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 1,215 results for author: <span class="mathjax">Kumar, 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=Kumar%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="Kumar, 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=Kumar%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="Kumar, 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=Kumar%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%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/2502.10842">arXiv:2502.10842</a> <span> [<a href="https://arxiv.org/pdf/2502.10842">pdf</a>, <a href="https://arxiv.org/format/2502.10842">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Mobile Robotic Multi-View Photometric Stereo </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Suryansh Kumar</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="2502.10842v1-abstract-short" style="display: inline;"> Multi-View Photometric Stereo (MVPS) is a popular method for fine-detailed 3D acquisition of an object from images. Despite its outstanding results on diverse material objects, a typical MVPS experimental setup requires a well-calibrated light source and a monocular camera installed on an immovable base. This restricts the use of MVPS on a movable platform, limiting us from taking MVPS benefits in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10842v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10842v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10842v1-abstract-full" style="display: none;"> Multi-View Photometric Stereo (MVPS) is a popular method for fine-detailed 3D acquisition of an object from images. Despite its outstanding results on diverse material objects, a typical MVPS experimental setup requires a well-calibrated light source and a monocular camera installed on an immovable base. This restricts the use of MVPS on a movable platform, limiting us from taking MVPS benefits in 3D acquisition for mobile robotics applications. To this end, we introduce a new mobile robotic system for MVPS. While the proposed system brings advantages, it introduces additional algorithmic challenges. Addressing them, in this paper, we further propose an incremental approach for mobile robotic MVPS. Our approach leverages a supervised learning setup to predict per-view surface normal, object depth, and per-pixel uncertainty in model-predicted results. A refined depth map per view is obtained by solving an MVPS-driven optimization problem proposed in this paper. Later, we fuse the refined depth map while tracking the camera pose w.r.t the reference frame to recover globally consistent object 3D geometry. Experimental results show the advantages of our robotic system and algorithm, featuring the local high-frequency surface detail recovery with globally consistent object shape. Our work is beyond any MVPS system yet presented, providing encouraging results on objects with unknown reflectance properties using fewer frames without a tiring calibration and installation process, enabling computationally efficient robotic automation approach to photogrammetry. The proposed approach is nearly 100 times computationally faster than the state-of-the-art MVPS methods such as [1, 2] while maintaining the similar results when tested on subjects taken from the benchmark DiLiGenT MV dataset [3]. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10842v1-abstract-full').style.display = 'none'; document.getElementById('2502.10842v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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">Accepted for publication in International Society Journal of Photogrammetry and Remote Sensing (ISPRS). 31 pages, 14 Figures, 5 Tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10354">arXiv:2502.10354</a> <span> [<a href="https://arxiv.org/pdf/2502.10354">pdf</a>, <a href="https://arxiv.org/format/2502.10354">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <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"> Dimension-free Score Matching and Time Bootstrapping for Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Syamantak Kumar</a>, <a href="/search/cs?searchtype=author&query=Nagaraj%2C+D">Dheeraj Nagaraj</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+P">Purnamrita Sarkar</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="2502.10354v1-abstract-short" style="display: inline;"> Diffusion models generate samples by estimating the score function of the target distribution at various noise levels. The model is trained using samples drawn from the target distribution, progressively adding noise. In this work, we establish the first (nearly) dimension-free sample complexity bounds for learning these score functions, achieving a double exponential improvement in dimension over… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10354v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10354v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10354v1-abstract-full" style="display: none;"> Diffusion models generate samples by estimating the score function of the target distribution at various noise levels. The model is trained using samples drawn from the target distribution, progressively adding noise. In this work, we establish the first (nearly) dimension-free sample complexity bounds for learning these score functions, achieving a double exponential improvement in dimension over prior results. A key aspect of our analysis is the use of a single function approximator to jointly estimate scores across noise levels, a critical feature of diffusion models in practice which enables generalization across timesteps. Our analysis introduces a novel martingale-based error decomposition and sharp variance bounds, enabling efficient learning from dependent data generated by Markov processes, which may be of independent interest. Building on these insights, we propose Bootstrapped Score Matching (BSM), a variance reduction technique that utilizes previously learned scores to improve accuracy at higher noise levels. These results provide crucial insights into the efficiency and effectiveness of diffusion models for generative modeling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10354v1-abstract-full').style.display = 'none'; document.getElementById('2502.10354v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10003">arXiv:2502.10003</a> <span> [<a href="https://arxiv.org/pdf/2502.10003">pdf</a>, <a href="https://arxiv.org/format/2502.10003">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SciClaimHunt: A Large Dataset for Evidence-based Scientific Claim Verification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sujit Kumar</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Anshul Sharma</a>, <a href="/search/cs?searchtype=author&query=Khincha%2C+S+H">Siddharth Hemant Khincha</a>, <a href="/search/cs?searchtype=author&query=Shroff%2C+G">Gargi Shroff</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+S+R">Sanasam Ranbir Singh</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+R">Rahul 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="2502.10003v1-abstract-short" style="display: inline;"> Verifying scientific claims presents a significantly greater challenge than verifying political or news-related claims. Unlike the relatively broad audience for political claims, the users of scientific claim verification systems can vary widely, ranging from researchers testing specific hypotheses to everyday users seeking information on a medication. Additionally, the evidence for scientific cla… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10003v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10003v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10003v1-abstract-full" style="display: none;"> Verifying scientific claims presents a significantly greater challenge than verifying political or news-related claims. Unlike the relatively broad audience for political claims, the users of scientific claim verification systems can vary widely, ranging from researchers testing specific hypotheses to everyday users seeking information on a medication. Additionally, the evidence for scientific claims is often highly complex, involving technical terminology and intricate domain-specific concepts that require specialized models for accurate verification. Despite considerable interest from the research community, there is a noticeable lack of large-scale scientific claim verification datasets to benchmark and train effective models. To bridge this gap, we introduce two large-scale datasets, SciClaimHunt and SciClaimHunt_Num, derived from scientific research papers. We propose several baseline models tailored for scientific claim verification to assess the effectiveness of these datasets. Additionally, we evaluate models trained on SciClaimHunt and SciClaimHunt_Num against existing scientific claim verification datasets to gauge their quality and reliability. Furthermore, we conduct human evaluations of the claims in proposed datasets and perform error analysis to assess the effectiveness of the proposed baseline models. Our findings indicate that SciClaimHunt and SciClaimHunt_Num serve as highly reliable resources for training models in scientific claim verification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10003v1-abstract-full').style.display = 'none'; document.getElementById('2502.10003v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09932">arXiv:2502.09932</a> <span> [<a href="https://arxiv.org/pdf/2502.09932">pdf</a>, <a href="https://arxiv.org/format/2502.09932">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"> AffectSRNet : Facial Emotion-Aware Super-Resolution Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rizvi%2C+S+S+A">Syed Sameen Ahmad Rizvi</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Soham Kumar</a>, <a href="/search/cs?searchtype=author&query=Seth%2C+A">Aryan Seth</a>, <a href="/search/cs?searchtype=author&query=Narang%2C+P">Pratik Narang</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="2502.09932v1-abstract-short" style="display: inline;"> Facial expression recognition (FER) systems in low-resolution settings face significant challenges in accurately identifying expressions due to the loss of fine-grained facial details. This limitation is especially problematic for applications like surveillance and mobile communications, where low image resolution is common and can compromise recognition accuracy. Traditional single-image face sup… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09932v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09932v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09932v1-abstract-full" style="display: none;"> Facial expression recognition (FER) systems in low-resolution settings face significant challenges in accurately identifying expressions due to the loss of fine-grained facial details. This limitation is especially problematic for applications like surveillance and mobile communications, where low image resolution is common and can compromise recognition accuracy. Traditional single-image face super-resolution (FSR) techniques, however, often fail to preserve the emotional intent of expressions, introducing distortions that obscure the original affective content. Given the inherently ill-posed nature of single-image super-resolution, a targeted approach is required to balance image quality enhancement with emotion retention. In this paper, we propose AffectSRNet, a novel emotion-aware super-resolution framework that reconstructs high-quality facial images from low-resolution inputs while maintaining the intensity and fidelity of facial expressions. Our method effectively bridges the gap between image resolution and expression accuracy by employing an expression-preserving loss function, specifically tailored for FER applications. Additionally, we introduce a new metric to assess emotion preservation in super-resolved images, providing a more nuanced evaluation of FER system performance in low-resolution scenarios. Experimental results on standard datasets, including CelebA, FFHQ, and Helen, demonstrate that AffectSRNet outperforms existing FSR approaches in both visual quality and emotion fidelity, highlighting its potential for integration into practical FER applications. This work not only improves image clarity but also ensures that emotion-driven applications retain their core functionality in suboptimal resolution environments, paving the way for broader adoption in FER systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09932v1-abstract-full').style.display = 'none'; document.getElementById('2502.09932v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.08773">arXiv:2502.08773</a> <span> [<a href="https://arxiv.org/pdf/2502.08773">pdf</a>, <a href="https://arxiv.org/format/2502.08773">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Universal Model Routing for Efficient LLM Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jitkrittum%2C+W">Wittawat Jitkrittum</a>, <a href="/search/cs?searchtype=author&query=Narasimhan%2C+H">Harikrishna Narasimhan</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A+S">Ankit Singh Rawat</a>, <a href="/search/cs?searchtype=author&query=Juneja%2C+J">Jeevesh Juneja</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zifeng Wang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+C">Chen-Yu Lee</a>, <a href="/search/cs?searchtype=author&query=Shenoy%2C+P">Pradeep Shenoy</a>, <a href="/search/cs?searchtype=author&query=Panigrahy%2C+R">Rina Panigrahy</a>, <a href="/search/cs?searchtype=author&query=Menon%2C+A+K">Aditya Krishna Menon</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sanjiv Kumar</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="2502.08773v1-abstract-short" style="display: inline;"> Large language models' significant advances in capabilities are accompanied by significant increases in inference costs. Model routing is a simple technique for reducing inference cost, wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the probl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08773v1-abstract-full').style.display = 'inline'; document.getElementById('2502.08773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08773v1-abstract-full" style="display: none;"> Large language models' significant advances in capabilities are accompanied by significant increases in inference costs. Model routing is a simple technique for reducing inference cost, wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose a new approach to this problem that relies on representing each LLM as a feature vector, derived based on predictions on a set of representative prompts. Based on this, we detail two effective strategies, relying on cluster-based routing and a learned cluster map respectively. We prove that these strategies are estimates of a theoretically optimal routing rule, and provide an excess risk bound to quantify their errors. Experiments on a range of public benchmarks show the effectiveness of the proposed strategies in routing amongst more than 30 unseen LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08773v1-abstract-full').style.display = 'none'; document.getElementById('2502.08773v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.08107">arXiv:2502.08107</a> <span> [<a href="https://arxiv.org/pdf/2502.08107">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> Machine Learning-Driven Volumetric Cloud Rendering: Procedural Shader Optimization and Dynamic Lighting in Unreal Engine for Realistic Atmospheric Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+S">Shruti Singh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shantanu Kumar</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="2502.08107v1-abstract-short" style="display: inline;"> This study advances real-time volumetric cloud rendering in Computer Graphics (CG) by developing a specialized shader in Unreal Engine (UE), focusing on realistic cloud modeling and lighting. By leveraging ray-casting-based lighting algorithms, this work demonstrates the practical application of a dual-layered procedural noise model, eliminating the need for conventional two-dimensional (2D) weath… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08107v1-abstract-full').style.display = 'inline'; document.getElementById('2502.08107v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08107v1-abstract-full" style="display: none;"> This study advances real-time volumetric cloud rendering in Computer Graphics (CG) by developing a specialized shader in Unreal Engine (UE), focusing on realistic cloud modeling and lighting. By leveraging ray-casting-based lighting algorithms, this work demonstrates the practical application of a dual-layered procedural noise model, eliminating the need for conventional two-dimensional (2D) weather textures. The shader allows for procedurally configured skies with a defined parameter set, offering flexibility for both artistic expression and realistic simulation. Empirical results reveal that the shader achieves an average rendering time of 35ms per frame while maintaining high visual accuracy and scene realism. Visual fidelity assessments indicate a 15% improvement in cloud realism over traditional 2D techniques, particularly in dynamic lighting scenarios. This research contributes to CG by bridging technical and aesthetic elements, enhancing real-time visual storytelling and immersion within gigital media environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08107v1-abstract-full').style.display = 'none'; document.getElementById('2502.08107v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.07634">arXiv:2502.07634</a> <span> [<a href="https://arxiv.org/pdf/2502.07634">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+S">Shruti Singh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shantanu Kumar</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="2502.07634v1-abstract-short" style="display: inline;"> This study investigates the impact of gradient compression on distributed training performance, focusing on sparsification and quantization techniques, including top-k, DGC, and QSGD. In baseline experiments, random-k compression results in severe performance degradation, highlighting its inefficacy. In contrast, using top-k and DGC at 50 times compression yields performance improvements, reducing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07634v1-abstract-full').style.display = 'inline'; document.getElementById('2502.07634v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.07634v1-abstract-full" style="display: none;"> This study investigates the impact of gradient compression on distributed training performance, focusing on sparsification and quantization techniques, including top-k, DGC, and QSGD. In baseline experiments, random-k compression results in severe performance degradation, highlighting its inefficacy. In contrast, using top-k and DGC at 50 times compression yields performance improvements, reducing perplexity by up to 0.06 compared to baseline. Experiments across 1, 2, and 4 workers demonstrate that conservative sparsification can have a regularizing effect, especially for smaller models, while compression ratios above 5000 times impair performance, particularly for DGC. Communication times are reduced across all compression methods, with top-k and DGC decreasing communication to negligible levels at high compression ratios. However, increased computation times offset this efficiency for top-k due to sorting demands, making it less scalable than DGC or QSGD. In convergence tests, sparsification techniques show accelerated convergence, requiring fewer epochs than the baseline, which has implications for computational savings. Although precision trade-offs emerge, floating point errors are mitigated by compression. This study's findings underscore the need to tune hyperparameters specifically for each compression technique to achieve optimal model performance, especially in distributed training systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07634v1-abstract-full').style.display = 'none'; document.getElementById('2502.07634v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.05233">arXiv:2502.05233</a> <span> [<a href="https://arxiv.org/pdf/2502.05233">pdf</a>, <a href="https://arxiv.org/format/2502.05233">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S+S">S Santosh Kumar</a>, <a href="/search/cs?searchtype=author&query=Gottimukkala%2C+R">Rishi Gottimukkala</a>, <a href="/search/cs?searchtype=author&query=Devidutta%2C+S">Supriya Devidutta</a>, <a href="/search/cs?searchtype=author&query=S%2C+K">Karthikeyan S</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="2502.05233v1-abstract-short" style="display: inline;"> This paper introduces a novel approach to efficiently feeding knowledge to language models (LLMs) during prediction by integrating retrieval and generation processes within a unified framework. While the Retrieval-Augmented Generation (RAG) model addresses gaps in LLMs' training data and knowledge limits, it is hindered by token limit restrictions and dependency on the retrieval system's accuracy.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05233v1-abstract-full').style.display = 'inline'; document.getElementById('2502.05233v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.05233v1-abstract-full" style="display: none;"> This paper introduces a novel approach to efficiently feeding knowledge to language models (LLMs) during prediction by integrating retrieval and generation processes within a unified framework. While the Retrieval-Augmented Generation (RAG) model addresses gaps in LLMs' training data and knowledge limits, it is hindered by token limit restrictions and dependency on the retrieval system's accuracy. Our proposed architecture incorporates in-context vectors (ICV) to overcome these challenges. ICV recasts in-context learning by using latent embeddings of LLMs to create a vector that captures essential task information. This vector is then used to shift the latent states of the LLM, enhancing the generation process without adding demonstration examples to the prompt. ICV directly integrates information into the model, enabling it to process this information more effectively. Our extensive experimental evaluation demonstrates that ICV outperforms standard in-context learning and fine-tuning across question-answering, information retrieval, and other tasks. This approach mitigates the limitations of current RAG models and offers a more robust solution for handling extensive and diverse datasets. Despite leveraging a fraction of the parameters, our ICV-enhanced model achieves competitive performance against models like LLaMA-3, Gemma, and Phi-3, significantly reducing computational costs and memory requirements. ICV reduces prompt length, is easy to control, surpasses token limitations, and is computationally efficient compared to fine-tuning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05233v1-abstract-full').style.display = 'none'; document.getElementById('2502.05233v1-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 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">Submitted to ACM TIST journal: under revision stage, 8 pages, 2 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> 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/2502.04423">arXiv:2502.04423</a> <span> [<a href="https://arxiv.org/pdf/2502.04423">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <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"> Primary Care Diagnoses as a Reliable Predictor for Orthopedic Surgical Interventions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Verma%2C+K">Khushboo Verma</a>, <a href="/search/cs?searchtype=author&query=Michels%2C+A">Alan Michels</a>, <a href="/search/cs?searchtype=author&query=Gumusaneli%2C+E">Ergi Gumusaneli</a>, <a href="/search/cs?searchtype=author&query=Chitnis%2C+S">Shilpa Chitnis</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S+S">Smita Sinha Kumar</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+C">Christopher Thompson</a>, <a href="/search/cs?searchtype=author&query=Esmail%2C+L">Lena Esmail</a>, <a href="/search/cs?searchtype=author&query=Srinivasan%2C+G">Guruprasath Srinivasan</a>, <a href="/search/cs?searchtype=author&query=Panchada%2C+C">Chandini Panchada</a>, <a href="/search/cs?searchtype=author&query=Guha%2C+S">Sushovan Guha</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Satwant Kumar</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="2502.04423v1-abstract-short" style="display: inline;"> Referral workflow inefficiencies, including misaligned referrals and delays, contribute to suboptimal patient outcomes and higher healthcare costs. In this study, we investigated the possibility of predicting procedural needs based on primary care diagnostic entries, thereby improving referral accuracy, streamlining workflows, and providing better care to patients. A de-identified dataset of 2,086… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04423v1-abstract-full').style.display = 'inline'; document.getElementById('2502.04423v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.04423v1-abstract-full" style="display: none;"> Referral workflow inefficiencies, including misaligned referrals and delays, contribute to suboptimal patient outcomes and higher healthcare costs. In this study, we investigated the possibility of predicting procedural needs based on primary care diagnostic entries, thereby improving referral accuracy, streamlining workflows, and providing better care to patients. A de-identified dataset of 2,086 orthopedic referrals from the University of Texas Health at Tyler was analyzed using machine learning models built on Base General Embeddings (BGE) for semantic extraction. To ensure real-world applicability, noise tolerance experiments were conducted, and oversampling techniques were employed to mitigate class imbalance. The selected optimum and parsimonious embedding model demonstrated high predictive accuracy (ROC-AUC: 0.874, Matthews Correlation Coefficient (MCC): 0.540), effectively distinguishing patients requiring surgical intervention. Dimensionality reduction techniques confirmed the model's ability to capture meaningful clinical relationships. A threshold sensitivity analysis identified an optimal decision threshold (0.30) to balance precision and recall, maximizing referral efficiency. In the predictive modeling analysis, the procedure rate increased from 11.27% to an optimal 60.1%, representing a 433% improvement with significant implications for operational efficiency and healthcare revenue. The results of our study demonstrate that referral optimization can enhance primary and surgical care integration. Through this approach, precise and timely predictions of procedural requirements can be made, thereby minimizing delays, improving surgical planning, and reducing administrative burdens. In addition, the findings highlight the potential of clinical decision support as a scalable solution for improving patient outcomes and the efficiency of the healthcare system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04423v1-abstract-full').style.display = 'none'; document.getElementById('2502.04423v1-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 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">ACM Class:</span> I.2.6; I.2.7; J.3; H.2.8 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.02494">arXiv:2502.02494</a> <span> [<a href="https://arxiv.org/pdf/2502.02494">pdf</a>, <a href="https://arxiv.org/format/2502.02494">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Analyzing Similarity Metrics for Data Selection for Language Model Pretraining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sam%2C+D">Dylan Sam</a>, <a href="/search/cs?searchtype=author&query=Chakrabarti%2C+A">Ayan Chakrabarti</a>, <a href="/search/cs?searchtype=author&query=Rostamizadeh%2C+A">Afshin Rostamizadeh</a>, <a href="/search/cs?searchtype=author&query=Ramalingam%2C+S">Srikumar Ramalingam</a>, <a href="/search/cs?searchtype=author&query=Citovsky%2C+G">Gui Citovsky</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sanjiv Kumar</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="2502.02494v2-abstract-short" style="display: inline;"> Similarity between training examples is used to curate pretraining datasets for language models by many methods -- for diversification and to select examples similar to high-quality data. However, similarity is typically measured with off-the-shelf embedding models that are generic or trained for tasks such as retrieval. This paper introduces a framework to analyze the suitability of embedding mod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02494v2-abstract-full').style.display = 'inline'; document.getElementById('2502.02494v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.02494v2-abstract-full" style="display: none;"> Similarity between training examples is used to curate pretraining datasets for language models by many methods -- for diversification and to select examples similar to high-quality data. However, similarity is typically measured with off-the-shelf embedding models that are generic or trained for tasks such as retrieval. This paper introduces a framework to analyze the suitability of embedding models specifically for data curation in the language model pretraining setting. We quantify the correlation between similarity in the embedding space to similarity in pretraining loss between different training examples, and how diversifying in the embedding space affects pretraining quality. We analyze a variety of embedding models in our framework, with experiments using the Pile dataset for pretraining a 1.7B parameter decoder-only language model. We find that the embedding models we consider are all useful for pretraining data curation. Moreover, a simple approach of averaging per-token embeddings proves to be surprisingly competitive with more sophisticated embedding models -- likely because the latter are not designed specifically for pretraining data curation. Indeed, we believe our analysis and evaluation framework can serve as a foundation for the design of embedding models that specifically reason about similarity in pretraining datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02494v2-abstract-full').style.display = 'none'; document.getElementById('2502.02494v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 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">14 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/2502.01588">arXiv:2502.01588</a> <span> [<a href="https://arxiv.org/pdf/2502.01588">pdf</a>, <a href="https://arxiv.org/format/2502.01588">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="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kaloga%2C+Y">Yacouba Kaloga</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shashi Kumar</a>, <a href="/search/cs?searchtype=author&query=Motlicek%2C+P">Petr Motlicek</a>, <a href="/search/cs?searchtype=author&query=Kodrasi%2C+I">Ina Kodrasi</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="2502.01588v1-abstract-short" style="display: inline;"> Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as the Connectionist Temporal Classification (CTC) and transducer-based models, suffer from peaky behavior and alignment inaccuracies. In this paper, we propose a no… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01588v1-abstract-full').style.display = 'inline'; document.getElementById('2502.01588v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.01588v1-abstract-full" style="display: none;"> Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as the Connectionist Temporal Classification (CTC) and transducer-based models, suffer from peaky behavior and alignment inaccuracies. In this paper, we propose a novel differentiable alignment framework based on one-dimensional optimal transport, enabling the model to learn a single alignment and perform ASR in an E2E manner. We introduce a pseudo-metric, called Sequence Optimal Transport Distance (SOTD), over the sequence space and discuss its theoretical properties. Based on the SOTD, we propose Optimal Temporal Transport Classification (OTTC) loss for ASR and contrast its behavior with CTC. Experimental results on the TIMIT, AMI, and LibriSpeech datasets show that our method considerably improves alignment performance, though with a trade-off in ASR performance when compared to CTC. We believe this work opens new avenues for seq2seq alignment research, providing a solid foundation for further exploration and development within the community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01588v1-abstract-full').style.display = 'none'; document.getElementById('2502.01588v1-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/2502.01108">arXiv:2502.01108</a> <span> [<a href="https://arxiv.org/pdf/2502.01108">pdf</a>, <a href="https://arxiv.org/format/2502.01108">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Saha%2C+M">Mithun Saha</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M+A">Maxwell A. Xu</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+W">Wanting Mao</a>, <a href="/search/cs?searchtype=author&query=Neupane%2C+S">Sameer Neupane</a>, <a href="/search/cs?searchtype=author&query=Rehg%2C+J+M">James M. Rehg</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Santosh Kumar</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="2502.01108v1-abstract-short" style="display: inline;"> Photoplethysmography (PPG)-based foundation models are gaining traction due to the widespread use of PPG in biosignal monitoring and their potential to generalize across diverse health applications. In this paper, we introduce Pulse-PPG, the first open-source PPG foundation model trained exclusively on raw PPG data collected over a 100-day field study with 120 participants. Existing PPG foundation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01108v1-abstract-full').style.display = 'inline'; document.getElementById('2502.01108v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.01108v1-abstract-full" style="display: none;"> Photoplethysmography (PPG)-based foundation models are gaining traction due to the widespread use of PPG in biosignal monitoring and their potential to generalize across diverse health applications. In this paper, we introduce Pulse-PPG, the first open-source PPG foundation model trained exclusively on raw PPG data collected over a 100-day field study with 120 participants. Existing PPG foundation models are either open-source but trained on clinical data or closed-source, limiting their applicability in real-world settings. We evaluate Pulse-PPG across multiple datasets and downstream tasks, comparing its performance against a state-of-the-art foundation model trained on clinical data. Our results demonstrate that Pulse-PPG, trained on uncurated field data, exhibits superior generalization across clinical and mobile health applications in both lab and field settings. This suggests that exposure to real-world variability enables the model to learn fine-grained representations, making it more adaptable across tasks. Furthermore, pre-training on field data surprisingly outperforms its pre-training on clinical data in many tasks, reinforcing the importance of training on real-world, diverse datasets. To encourage further advancements in robust foundation models leveraging field data, we plan to release Pulse-PPG, providing researchers with a powerful resource for developing more generalizable PPG-based models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01108v1-abstract-full').style.display = 'none'; document.getElementById('2502.01108v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The first two listed authors contributed equally to this research</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.00050">arXiv:2502.00050</a> <span> [<a href="https://arxiv.org/pdf/2502.00050">pdf</a>, <a href="https://arxiv.org/format/2502.00050">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> DISC: Dataset for Analyzing Driving Styles In Simulated Crashes for Mixed Autonomy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S+S+S">Sandip Sharan Senthil Kumar</a>, <a href="/search/cs?searchtype=author&query=Thalapanane%2C+S">Sandeep Thalapanane</a>, <a href="/search/cs?searchtype=author&query=Peethambari%2C+G+N+A+D">Guru Nandhan Appiya Dilipkumar Peethambari</a>, <a href="/search/cs?searchtype=author&query=SriHari%2C+S">Sourang SriHari</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+L">Laura Zheng</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+M+C">Ming C. Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.00050v1-abstract-short" style="display: inline;"> Handling pre-crash scenarios is still a major challenge for self-driving cars due to limited practical data and human-driving behavior datasets. We introduce DISC (Driving Styles In Simulated Crashes), one of the first datasets designed to capture various driving styles and behaviors in pre-crash scenarios for mixed autonomy analysis. DISC includes over 8 classes of driving styles/behaviors from h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00050v1-abstract-full').style.display = 'inline'; document.getElementById('2502.00050v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.00050v1-abstract-full" style="display: none;"> Handling pre-crash scenarios is still a major challenge for self-driving cars due to limited practical data and human-driving behavior datasets. We introduce DISC (Driving Styles In Simulated Crashes), one of the first datasets designed to capture various driving styles and behaviors in pre-crash scenarios for mixed autonomy analysis. DISC includes over 8 classes of driving styles/behaviors from hundreds of drivers navigating a simulated vehicle through a virtual city, encountering rare-event traffic scenarios. This dataset enables the classification of pre-crash human driving behaviors in unsafe conditions, supporting individualized trajectory prediction based on observed driving patterns. By utilizing a custom-designed VR-based in-house driving simulator, TRAVERSE, data was collected through a driver-centric study involving human drivers encountering twelve simulated accident scenarios. This dataset fills a critical gap in human-centric driving data for rare events involving interactions with autonomous vehicles. It enables autonomous systems to better react to human drivers and optimize trajectory prediction in mixed autonomy environments involving both human-driven and self-driving cars. In addition, individual driving behaviors are classified through a set of standardized questionnaires, carefully designed to identify and categorize driving behavior traits. We correlate data features with driving behaviors, showing that the simulated environment reflects real-world driving styles. DISC is the first dataset to capture how various driving styles respond to accident scenarios, offering significant potential to enhance autonomous vehicle safety and driving behavior analysis in mixed autonomy environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00050v1-abstract-full').style.display = 'none'; document.getElementById('2502.00050v1-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 January, 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/2501.18748">arXiv:2501.18748</a> <span> [<a href="https://arxiv.org/pdf/2501.18748">pdf</a>, <a href="https://arxiv.org/format/2501.18748">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/10.1145/3706598.3713785">10.1145/3706598.3713785 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Dancing With Chains: Ideating Under Constraints With UIDEC in UI/UX Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shokrizadeh%2C+A">Atefeh Shokrizadeh</a>, <a href="/search/cs?searchtype=author&query=Tadjuidje%2C+B+B">Boniface Bahati Tadjuidje</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shivam Kumar</a>, <a href="/search/cs?searchtype=author&query=Kamble%2C+S">Sohan Kamble</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+J">Jinghui Cheng</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="2501.18748v1-abstract-short" style="display: inline;"> UI/UX designers often work under constraints like brand identity, design norms, and industry guidelines. How these constraints impact designers' ideation and exploration processes should be addressed in creativity-support tools for design. Through an exploratory interview study, we identified three designer personas with varying views on having constraints in the ideation process, which guided the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18748v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18748v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18748v1-abstract-full" style="display: none;"> UI/UX designers often work under constraints like brand identity, design norms, and industry guidelines. How these constraints impact designers' ideation and exploration processes should be addressed in creativity-support tools for design. Through an exploratory interview study, we identified three designer personas with varying views on having constraints in the ideation process, which guided the creation of UIDEC, a GenAI-powered tool for supporting creativity under constraints. UIDEC allows designers to specify project details, such as purpose, target audience, industry, and design styles, based on which it generates diverse design examples that adhere to these constraints, with minimal need to write prompts. In a user evaluation involving designers representing the identified personas, participants found UIDEC compatible with their existing ideation process and useful for creative inspiration, especially when starting new projects. Our work provides design implications to AI-powered tools that integrate constraints during UI/UX design ideation to support creativity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18748v1-abstract-full').style.display = 'none'; document.getElementById('2501.18748v1-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 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">23 pages, 8 figures, CHI 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/2501.18444">arXiv:2501.18444</a> <span> [<a href="https://arxiv.org/pdf/2501.18444">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Adaptive Object Detection for Indoor Navigation Assistance: A Performance Evaluation of Real-Time Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pratap%2C+A">Abhinav Pratap</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sushant Kumar</a>, <a href="/search/cs?searchtype=author&query=Chakravarty%2C+S">Suchinton Chakravarty</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="2501.18444v1-abstract-short" style="display: inline;"> This study addresses the need for accurate and efficient object detection in assistive technologies for visually impaired individuals. We evaluate four real-time object detection algorithms YOLO, SSD, Faster R-CNN, and Mask R-CNN within the context of indoor navigation assistance. Using the Indoor Objects Detection dataset, we analyze detection accuracy, processing speed, and adaptability to indoo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18444v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18444v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18444v1-abstract-full" style="display: none;"> This study addresses the need for accurate and efficient object detection in assistive technologies for visually impaired individuals. We evaluate four real-time object detection algorithms YOLO, SSD, Faster R-CNN, and Mask R-CNN within the context of indoor navigation assistance. Using the Indoor Objects Detection dataset, we analyze detection accuracy, processing speed, and adaptability to indoor environments. Our findings highlight the trade-offs between precision and efficiency, offering insights into selecting optimal algorithms for realtime assistive navigation. This research advances adaptive machine learning applications, enhancing indoor navigation solutions for the visually impaired and promoting accessibility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18444v1-abstract-full').style.display = 'none'; document.getElementById('2501.18444v1-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 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">5 pages, 2 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.14964">arXiv:2501.14964</a> <span> [<a href="https://arxiv.org/pdf/2501.14964">pdf</a>, <a href="https://arxiv.org/format/2501.14964">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"> Personalized Layer Selection for Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+K">Kartik Sharma</a>, <a href="/search/cs?searchtype=author&query=Mohan%2C+V+R">Vineeth Rakesh Mohan</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Y">Yingtong Dou</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Srijan Kumar</a>, <a href="/search/cs?searchtype=author&query=Das%2C+M">Mahashweta 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="2501.14964v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14964v1-abstract-full').style.display = 'inline'; document.getElementById('2501.14964v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14964v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect1, to select the optimal representation layer to classify each node. In particular, we identify a prototype representation of each class in a transformed GNN layer and then, classify using the layer where the distance is smallest to a class prototype after normalizing with that layer's variance. Results on 10 datasets and 3 different GNNs show that we significantly improve the node classification accuracy of GNNs in a plug-and-play manner. We also find that using variable layers for prediction enables GNNs to be deeper and more robust to poisoning attacks. We hope this work can inspire future works to learn more adaptive and personalized graph representations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14964v1-abstract-full').style.display = 'none'; document.getElementById('2501.14964v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.13831">arXiv:2501.13831</a> <span> [<a href="https://arxiv.org/pdf/2501.13831">pdf</a>, <a href="https://arxiv.org/format/2501.13831">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"> Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hao Zhang</a>, <a href="/search/cs?searchtype=author&query=Stahlberg%2C+F">Felix Stahlberg</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shankar Kumar</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="2501.13831v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) excel at rewriting tasks such as text style transfer and grammatical error correction. While there is considerable overlap between the inputs and outputs in these tasks, the decoding cost still increases with output length, regardless of the amount of overlap. By leveraging the overlap between the input and the output, Kaneko and Okazaki (2023) proposed model-agnostic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13831v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13831v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13831v1-abstract-full" style="display: none;"> Large Language Models (LLMs) excel at rewriting tasks such as text style transfer and grammatical error correction. While there is considerable overlap between the inputs and outputs in these tasks, the decoding cost still increases with output length, regardless of the amount of overlap. By leveraging the overlap between the input and the output, Kaneko and Okazaki (2023) proposed model-agnostic edit span representations to compress the rewrites to save computation. They reported an output length reduction rate of nearly 80% with minimal accuracy impact in four rewriting tasks. In this paper, we propose alternative edit phrase representations inspired by phrase-based statistical machine translation. We systematically compare our phrasal representations with their span representations. We apply the LLM rewriting model to the task of Automatic Speech Recognition (ASR) post editing and show that our target-phrase-only edit representation has the best efficiency-accuracy trade-off. On the LibriSpeech test set, our method closes 50-60% of the WER gap between the edit span model and the full rewrite model while losing only 10-20% of the length reduction rate of the edit span model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13831v1-abstract-full').style.display = 'none'; document.getElementById('2501.13831v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted by ICASSP 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/2501.13051">arXiv:2501.13051</a> <span> [<a href="https://arxiv.org/pdf/2501.13051">pdf</a>, <a href="https://arxiv.org/format/2501.13051">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"> Column-Oriented Datalog on the GPU </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yihao Sun</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sidharth Kumar</a>, <a href="/search/cs?searchtype=author&query=Gilray%2C+T">Thomas Gilray</a>, <a href="/search/cs?searchtype=author&query=Micinski%2C+K">Kristopher Micinski</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="2501.13051v1-abstract-short" style="display: inline;"> Datalog is a logic programming language widely used in knowledge representation and reasoning (KRR), program analysis, and social media mining due to its expressiveness and high performance. Traditionally, Datalog engines use either row-oriented or column-oriented storage. Engines like VLog and Nemo favor column-oriented storage for efficiency on limited-resource machines, while row-oriented engin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13051v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13051v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13051v1-abstract-full" style="display: none;"> Datalog is a logic programming language widely used in knowledge representation and reasoning (KRR), program analysis, and social media mining due to its expressiveness and high performance. Traditionally, Datalog engines use either row-oriented or column-oriented storage. Engines like VLog and Nemo favor column-oriented storage for efficiency on limited-resource machines, while row-oriented engines like Souffle use advanced data structures with locking to perform better on multi-core CPUs. The advent of modern datacenter GPUs, such as the NVIDIA H100 with its ability to run over 16k threads simultaneously and high memory bandwidth, has reopened the debate on which storage layout is more effective. This paper presents the first column-oriented Datalog engines tailored to the strengths of modern GPUs. We present VFLog, a CUDA-based Datalog runtime library with a column-oriented GPU datastructure that supports all necessary relational algebra operations. Our results demonstrate over 200x performance gains over SOTA CPU-based column-oriented Datalog engines and a 2.5x speedup over GPU Datalog engines in various workloads, including KRR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13051v1-abstract-full').style.display = 'none'; document.getElementById('2501.13051v1-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 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/2501.13020">arXiv:2501.13020</a> <span> [<a href="https://arxiv.org/pdf/2501.13020">pdf</a>, <a href="https://arxiv.org/format/2501.13020">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Characterizing Collective Efforts in Content Sharing and Quality Control for ADHD-relevant Content on Video-sharing Platforms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+H+%27">Hanxiu 'Hazel' Zhu</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+A+S">Avanthika Senthil Kumar</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Sihang Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ru Wang</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+X">Xin Tong</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yuhang Zhao</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="2501.13020v1-abstract-short" style="display: inline;"> Video-sharing platforms (VSPs) have become increasingly important for individuals with ADHD to recognize symptoms, acquire knowledge, and receive support. While videos offer rich information and high engagement, they also present unique challenges, such as information quality and accessibility issues to users with ADHD. However, little work has thoroughly examined the video content quality and acc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13020v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13020v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13020v1-abstract-full" style="display: none;"> Video-sharing platforms (VSPs) have become increasingly important for individuals with ADHD to recognize symptoms, acquire knowledge, and receive support. While videos offer rich information and high engagement, they also present unique challenges, such as information quality and accessibility issues to users with ADHD. However, little work has thoroughly examined the video content quality and accessibility issues, the impact, and the control strategies in the ADHD community. We fill this gap by systematically collecting 373 ADHD-relevant videos with comments from YouTube and TikTok and analyzing the data with a mixed method. Our study identified the characteristics of ADHD-relevant videos on VSPs (e.g., creator types, video presentation forms, quality issues) and revealed the collective efforts of creators and viewers in video quality control, such as authority building, collective quality checking, and accessibility improvement. We further derive actionable design implications for VSPs to offer more reliable and ADHD-friendly contents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13020v1-abstract-full').style.display = 'none'; document.getElementById('2501.13020v1-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 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/2501.12756">arXiv:2501.12756</a> <span> [<a href="https://arxiv.org/pdf/2501.12756">pdf</a>, <a href="https://arxiv.org/format/2501.12756">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> </div> </div> <p class="title is-5 mathjax"> A topology optimisation framework to design test specimens for one-shot identification or discovery of material models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ghouli%2C+S">Saeid Ghouli</a>, <a href="/search/cs?searchtype=author&query=Flaschel%2C+M">Moritz Flaschel</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Siddhant Kumar</a>, <a href="/search/cs?searchtype=author&query=De+Lorenzis%2C+L">Laura De Lorenzis</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="2501.12756v1-abstract-short" style="display: inline;"> The increasing availability of full-field displacement data from imaging techniques in experimental mechanics is determining a gradual shift in the paradigm of material model calibration and discovery, from using several simple-geometry tests towards a few, or even one single test with complicated geometry. The feasibility of such a "one-shot" calibration or discovery heavily relies upon the richn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12756v1-abstract-full').style.display = 'inline'; document.getElementById('2501.12756v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.12756v1-abstract-full" style="display: none;"> The increasing availability of full-field displacement data from imaging techniques in experimental mechanics is determining a gradual shift in the paradigm of material model calibration and discovery, from using several simple-geometry tests towards a few, or even one single test with complicated geometry. The feasibility of such a "one-shot" calibration or discovery heavily relies upon the richness of the measured displacement data, i.e., their ability to probe the space of the state variables and the stress space (whereby the stresses depend on the constitutive law being sought) to an extent sufficient for an accurate and robust calibration or discovery process. The richness of the displacement data is in turn directly governed by the specimen geometry. In this paper, we propose a density-based topology optimisation framework to optimally design the geometry of the target specimen for calibration of an anisotropic elastic material model. To this end, we perform automatic, high-resolution specimen design by maximising the robustness of the solution of the inverse problem, i.e., the identified material parameters, given noisy displacement measurements from digital image correlation. We discuss the choice of the cost function and the design of the topology optimisation framework, and we analyse a range of optimised topologies generated for the identification of isotropic and anisotropic elastic responses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12756v1-abstract-full').style.display = 'none'; document.getElementById('2501.12756v1-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 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">30 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/2501.12214">arXiv:2501.12214</a> <span> [<a href="https://arxiv.org/pdf/2501.12214">pdf</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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Improving robot understanding using conversational AI: demonstration and feasibility study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shikhar Kumar</a>, <a href="/search/cs?searchtype=author&query=Edan%2C+Y">Yael Edan</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="2501.12214v1-abstract-short" style="display: inline;"> Explanations constitute an important aspect of successful human robot interactions and can enhance robot understanding. To improve the understanding of the robot, we have developed four levels of explanation (LOE) based on two questions: what needs to be explained, and why the robot has made a particular decision. The understandable robot requires a communicative action when there is disparity bet… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12214v1-abstract-full').style.display = 'inline'; document.getElementById('2501.12214v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.12214v1-abstract-full" style="display: none;"> Explanations constitute an important aspect of successful human robot interactions and can enhance robot understanding. To improve the understanding of the robot, we have developed four levels of explanation (LOE) based on two questions: what needs to be explained, and why the robot has made a particular decision. The understandable robot requires a communicative action when there is disparity between the human s mental model of the robot and the robots state of mind. This communicative action was generated by utilizing a conversational AI platform to generate explanations. An adaptive dialog was implemented for transition from one LOE to another. Here, we demonstrate the adaptive dialog in a collaborative task with errors and provide results of a feasibility study with users. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12214v1-abstract-full').style.display = 'none'; document.getElementById('2501.12214v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">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">40th Anniversary, IEEE International Conference on Robotics and Automation,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/2501.10066">arXiv:2501.10066</a> <span> [<a href="https://arxiv.org/pdf/2501.10066">pdf</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="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> A Comprehensive Insights into Drones: History, Classification, Architecture, Navigation, Applications, Challenges, and Future Trends </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+R">Ruchita Singh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sandeep Kumar</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="2501.10066v1-abstract-short" style="display: inline;"> Unmanned Aerial Vehicles (UAVs), commonly known as Drones, are one of 21st century most transformative technologies. Emerging first for military use, advancements in materials, electronics, and software have catapulted drones into multipurpose tools for a wide range of industries. In this paper, we have covered the history, taxonomy, architecture, navigation systems and branched activities for the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10066v1-abstract-full').style.display = 'inline'; document.getElementById('2501.10066v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.10066v1-abstract-full" style="display: none;"> Unmanned Aerial Vehicles (UAVs), commonly known as Drones, are one of 21st century most transformative technologies. Emerging first for military use, advancements in materials, electronics, and software have catapulted drones into multipurpose tools for a wide range of industries. In this paper, we have covered the history, taxonomy, architecture, navigation systems and branched activities for the same. It explores important future trends like autonomous navigation, AI integration, and obstacle avoidance systems, emphasizing how they contribute to improving the efficiency and versatility of drones. It also looks at the major challenges like technical, environmental, economic, regulatory and ethical, that limit the actual take-up of drones, as well as trends that are likely to mitigate these obstacles in the future. This work offers a structured synthesis of existing studies and perspectives that enable insights about how drones will transform agriculture, logistics, healthcare, disaster management, and other areas, while also identifying new opportunities for innovation and development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10066v1-abstract-full').style.display = 'none'; document.getElementById('2501.10066v1-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 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/2501.09999">arXiv:2501.09999</a> <span> [<a href="https://arxiv.org/pdf/2501.09999">pdf</a>, <a href="https://arxiv.org/format/2501.09999">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning for Early Alzheimer Disease Detection with MRI Scans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rafsan%2C+M">Mohammad Rafsan</a>, <a href="/search/cs?searchtype=author&query=Oraby%2C+T">Tamer Oraby</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+U">Upal Roy</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sanjeev Kumar</a>, <a href="/search/cs?searchtype=author&query=Rodrigo%2C+H">Hansapani Rodrigo</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="2501.09999v1-abstract-short" style="display: inline;"> Alzheimer's Disease is a neurodegenerative condition characterized by dementia and impairment in neurological function. The study primarily focuses on the individuals above age 40, affecting their memory, behavior, and cognitive processes of the brain. Alzheimer's disease requires diagnosis by a detailed assessment of MRI scans and neuropsychological tests of the patients. This project compares ex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09999v1-abstract-full').style.display = 'inline'; document.getElementById('2501.09999v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.09999v1-abstract-full" style="display: none;"> Alzheimer's Disease is a neurodegenerative condition characterized by dementia and impairment in neurological function. The study primarily focuses on the individuals above age 40, affecting their memory, behavior, and cognitive processes of the brain. Alzheimer's disease requires diagnosis by a detailed assessment of MRI scans and neuropsychological tests of the patients. This project compares existing deep learning models in the pursuit of enhancing the accuracy and efficiency of AD diagnosis, specifically focusing on the Convolutional Neural Network, Bayesian Convolutional Neural Network, and the U-net model with the Open Access Series of Imaging Studies brain MRI dataset. Besides, to ensure robustness and reliability in the model evaluations, we address the challenge of imbalance in data. We then perform rigorous evaluation to determine strengths and weaknesses for each model by considering sensitivity, specificity, and computational efficiency. This comparative analysis would shed light on the future role of AI in revolutionizing AD diagnostics but also paved ways for future innovation in medical imaging and the management of neurodegenerative diseases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09999v1-abstract-full').style.display = 'none'; document.getElementById('2501.09999v1-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 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/2501.09878">arXiv:2501.09878</a> <span> [<a href="https://arxiv.org/pdf/2501.09878">pdf</a>, <a href="https://arxiv.org/format/2501.09878">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Teeti%2C+I">Izzeddin Teeti</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+A">Aniket Thomas</a>, <a href="/search/cs?searchtype=author&query=Monga%2C+M">Munish Monga</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sachin Kumar</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+U">Uddeshya Singh</a>, <a href="/search/cs?searchtype=author&query=Bradley%2C+A">Andrew Bradley</a>, <a href="/search/cs?searchtype=author&query=Banerjee%2C+B">Biplab Banerjee</a>, <a href="/search/cs?searchtype=author&query=Cuzzolin%2C+F">Fabio Cuzzolin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.09878v1-abstract-short" style="display: inline;"> We present ASTRA (A} Scene-aware TRAnsformer-based model for trajectory prediction), a light-weight pedestrian trajectory forecasting model that integrates the scene context, spatial dynamics, social inter-agent interactions and temporal progressions for precise forecasting. We utilised a U-Net-based feature extractor, via its latent vector representation, to capture scene representations and a gr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09878v1-abstract-full').style.display = 'inline'; document.getElementById('2501.09878v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.09878v1-abstract-full" style="display: none;"> We present ASTRA (A} Scene-aware TRAnsformer-based model for trajectory prediction), a light-weight pedestrian trajectory forecasting model that integrates the scene context, spatial dynamics, social inter-agent interactions and temporal progressions for precise forecasting. We utilised a U-Net-based feature extractor, via its latent vector representation, to capture scene representations and a graph-aware transformer encoder for capturing social interactions. These components are integrated to learn an agent-scene aware embedding, enabling the model to learn spatial dynamics and forecast the future trajectory of pedestrians. The model is designed to produce both deterministic and stochastic outcomes, with the stochastic predictions being generated by incorporating a Conditional Variational Auto-Encoder (CVAE). ASTRA also proposes a simple yet effective weighted penalty loss function, which helps to yield predictions that outperform a wide array of state-of-the-art deterministic and generative models. ASTRA demonstrates an average improvement of 27%/10% in deterministic/stochastic settings on the ETH-UCY dataset, and 26% improvement on the PIE dataset, respectively, along with seven times fewer parameters than the existing state-of-the-art model (see Figure 1). Additionally, the model's versatility allows it to generalize across different perspectives, such as Bird's Eye View (BEV) and Ego-Vehicle View (EVV). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09878v1-abstract-full').style.display = 'none'; document.getElementById('2501.09878v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 January, 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/2501.09528">arXiv:2501.09528</a> <span> [<a href="https://arxiv.org/pdf/2501.09528">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Comprehensive Survey of QML: From Data Analysis to Algorithmic Advancements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tomar%2C+S">Sahil Tomar</a>, <a href="/search/cs?searchtype=author&query=Tripathi%2C+R">Rajeshwar Tripathi</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sandeep Kumar</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="2501.09528v1-abstract-short" style="display: inline;"> Quantum Machine Learning represents a paradigm shift at the intersection of Quantum Computing and Machine Learning, leveraging quantum phenomena such as superposition, entanglement, and quantum parallelism to address the limitations of classical approaches in processing high-dimensional and large-scale datasets. This survey provides a comprehensive analysis of Quantum Machine Learning, detailing f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09528v1-abstract-full').style.display = 'inline'; document.getElementById('2501.09528v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.09528v1-abstract-full" style="display: none;"> Quantum Machine Learning represents a paradigm shift at the intersection of Quantum Computing and Machine Learning, leveraging quantum phenomena such as superposition, entanglement, and quantum parallelism to address the limitations of classical approaches in processing high-dimensional and large-scale datasets. This survey provides a comprehensive analysis of Quantum Machine Learning, detailing foundational concepts, algorithmic advancements, and their applications across domains such as healthcare, finance, and quantum chemistry. Key techniques, including Quantum Support Vector Machine, Quantum Neural Network, Quantum Decision Trees, and hybrid quantum-classical models, are explored with a focus on their theoretical foundations, computational benefits, and comparative performance against classical counterparts. While the potential for exponential speedups and enhanced efficiency is evident, the field faces significant challenges, including hardware constraints, noise, and limited qubit coherence in the current era of Noisy Intermediate-Scale Quantum devices. Emerging solutions, such as error mitigation techniques, hybrid frameworks, and advancements in quantum hardware, are discussed as critical enablers for scalable and fault-tolerant Quantum Machine Learning systems. By synthesizing state-of-the-art developments and identifying research gaps, this survey aims to provide a foundational resource for advancing Quantum Machine Learning toward practical, real-world applications in tackling computationally intensive problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09528v1-abstract-full').style.display = 'none'; document.getElementById('2501.09528v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 January, 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/2501.09136">arXiv:2501.09136</a> <span> [<a href="https://arxiv.org/pdf/2501.09136">pdf</a>, <a href="https://arxiv.org/format/2501.09136">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Aditi Singh</a>, <a href="/search/cs?searchtype=author&query=Ehtesham%2C+A">Abul Ehtesham</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Saket Kumar</a>, <a href="/search/cs?searchtype=author&query=Khoei%2C+T+T">Tala Talaei Khoei</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="2501.09136v3-abstract-short" style="display: inline;"> Large Language Models (LLMs) have revolutionized artificial intelligence (AI) by enabling human like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real time queries, resulting in outdated or inaccurate outputs. Retrieval Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09136v3-abstract-full').style.display = 'inline'; document.getElementById('2501.09136v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.09136v3-abstract-full" style="display: none;"> Large Language Models (LLMs) have revolutionized artificial intelligence (AI) by enabling human like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real time queries, resulting in outdated or inaccurate outputs. Retrieval Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multistep reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multiagent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows to meet complex task requirements. This integration enables Agentic RAG systems to deliver unparalleled flexibility, scalability, and context awareness across diverse applications. This survey provides a comprehensive exploration of Agentic RAG, beginning with its foundational principles and the evolution of RAG paradigms. It presents a detailed taxonomy of Agentic RAG architectures, highlights key applications in industries such as healthcare, finance, and education, and examines practical implementation strategies. Additionally, it addresses challenges in scaling these systems, ensuring ethical decision making, and optimizing performance for real-world applications, while providing detailed insights into frameworks and tools for implementing Agentic RAG. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09136v3-abstract-full').style.display = 'none'; document.getElementById('2501.09136v3-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">v1</span> submitted 15 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/2501.08035">arXiv:2501.08035</a> <span> [<a href="https://arxiv.org/pdf/2501.08035">pdf</a>, <a href="https://arxiv.org/format/2501.08035">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"> READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+R">Rohit Sharma</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shanu Kumar</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+A">Avinash Kumar</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="2501.08035v1-abstract-short" style="display: inline;"> Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often expensive and time-consuming, whereas collecting unlabeled data using some heuristics is relatively much cheaper for any task. Therefore, this paper proposes a method… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08035v1-abstract-full').style.display = 'inline'; document.getElementById('2501.08035v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.08035v1-abstract-full" style="display: none;"> Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often expensive and time-consuming, whereas collecting unlabeled data using some heuristics is relatively much cheaper for any task. Therefore, this paper proposes a method that encapsulates reinforcement learning-based text generation and semi-supervised adversarial learning approaches in a novel way to improve the model's performance. Our method READ, Reinforcement-based Adversarial learning, utilizes an unlabeled dataset to generate diverse synthetic text through reinforcement learning, improving the model's generalization capability using adversarial learning. Our experimental results show that READ outperforms the existing state-of-art methods on multiple datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08035v1-abstract-full').style.display = 'none'; document.getElementById('2501.08035v1-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/2501.07238">arXiv:2501.07238</a> <span> [<a href="https://arxiv.org/pdf/2501.07238">pdf</a>, <a href="https://arxiv.org/format/2501.07238">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Lessons From Red Teaming 100 Generative AI Products </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bullwinkel%2C+B">Blake Bullwinkel</a>, <a href="/search/cs?searchtype=author&query=Minnich%2C+A">Amanda Minnich</a>, <a href="/search/cs?searchtype=author&query=Chawla%2C+S">Shiven Chawla</a>, <a href="/search/cs?searchtype=author&query=Lopez%2C+G">Gary Lopez</a>, <a href="/search/cs?searchtype=author&query=Pouliot%2C+M">Martin Pouliot</a>, <a href="/search/cs?searchtype=author&query=Maxwell%2C+W">Whitney Maxwell</a>, <a href="/search/cs?searchtype=author&query=de+Gruyter%2C+J">Joris de Gruyter</a>, <a href="/search/cs?searchtype=author&query=Pratt%2C+K">Katherine Pratt</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+S">Saphir Qi</a>, <a href="/search/cs?searchtype=author&query=Chikanov%2C+N">Nina Chikanov</a>, <a href="/search/cs?searchtype=author&query=Lutz%2C+R">Roman Lutz</a>, <a href="/search/cs?searchtype=author&query=Dheekonda%2C+R+S+R">Raja Sekhar Rao Dheekonda</a>, <a href="/search/cs?searchtype=author&query=Jagdagdorj%2C+B">Bolor-Erdene Jagdagdorj</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+E">Eugenia Kim</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Justin Song</a>, <a href="/search/cs?searchtype=author&query=Hines%2C+K">Keegan Hines</a>, <a href="/search/cs?searchtype=author&query=Jones%2C+D">Daniel Jones</a>, <a href="/search/cs?searchtype=author&query=Severi%2C+G">Giorgio Severi</a>, <a href="/search/cs?searchtype=author&query=Lundeen%2C+R">Richard Lundeen</a>, <a href="/search/cs?searchtype=author&query=Vaughan%2C+S">Sam Vaughan</a>, <a href="/search/cs?searchtype=author&query=Westerhoff%2C+V">Victoria Westerhoff</a>, <a href="/search/cs?searchtype=author&query=Bryan%2C+P">Pete Bryan</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+R+S+S">Ram Shankar Siva Kumar</a>, <a href="/search/cs?searchtype=author&query=Zunger%2C+Y">Yonatan Zunger</a>, <a href="/search/cs?searchtype=author&query=Kawaguchi%2C+C">Chang Kawaguchi</a> , et al. (1 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="2501.07238v1-abstract-short" style="display: inline;"> In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted. Based on our experience red teaming over 100 generative AI products at Microsoft, we present our internal threat model ontology and eight main lessons we have lea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07238v1-abstract-full').style.display = 'inline'; document.getElementById('2501.07238v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07238v1-abstract-full" style="display: none;"> In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted. Based on our experience red teaming over 100 generative AI products at Microsoft, we present our internal threat model ontology and eight main lessons we have learned: 1. Understand what the system can do and where it is applied 2. You don't have to compute gradients to break an AI system 3. AI red teaming is not safety benchmarking 4. Automation can help cover more of the risk landscape 5. The human element of AI red teaming is crucial 6. Responsible AI harms are pervasive but difficult to measure 7. LLMs amplify existing security risks and introduce new ones 8. The work of securing AI systems will never be complete By sharing these insights alongside case studies from our operations, we offer practical recommendations aimed at aligning red teaming efforts with real world risks. We also highlight aspects of AI red teaming that we believe are often misunderstood and discuss open questions for the field to consider. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07238v1-abstract-full').style.display = 'none'; document.getElementById('2501.07238v1-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 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/2501.05997">arXiv:2501.05997</a> <span> [<a href="https://arxiv.org/pdf/2501.05997">pdf</a>, <a href="https://arxiv.org/format/2501.05997">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"> Minimizing Occlusion Effect on Multi-View Camera Perception in BEV with Multi-Sensor Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sanjay Kumar</a>, <a href="/search/cs?searchtype=author&query=Truong%2C+H">Hiep Truong</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+S">Sushil Sharma</a>, <a href="/search/cs?searchtype=author&query=Sistu%2C+G">Ganesh Sistu</a>, <a href="/search/cs?searchtype=author&query=Scanlan%2C+T">Tony Scanlan</a>, <a href="/search/cs?searchtype=author&query=Grua%2C+E">Eoin Grua</a>, <a href="/search/cs?searchtype=author&query=Eising%2C+C">Ciar谩n Eising</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="2501.05997v1-abstract-short" style="display: inline;"> Autonomous driving technology is rapidly evolving, offering the potential for safer and more efficient transportation. However, the performance of these systems can be significantly compromised by the occlusion on sensors due to environmental factors like dirt, dust, rain, and fog. These occlusions severely affect vision-based tasks such as object detection, vehicle segmentation, and lane recognit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05997v1-abstract-full').style.display = 'inline'; document.getElementById('2501.05997v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05997v1-abstract-full" style="display: none;"> Autonomous driving technology is rapidly evolving, offering the potential for safer and more efficient transportation. However, the performance of these systems can be significantly compromised by the occlusion on sensors due to environmental factors like dirt, dust, rain, and fog. These occlusions severely affect vision-based tasks such as object detection, vehicle segmentation, and lane recognition. In this paper, we investigate the impact of various kinds of occlusions on camera sensor by projecting their effects from multi-view camera images of the nuScenes dataset into the Bird's-Eye View (BEV) domain. This approach allows us to analyze how occlusions spatially distribute and influence vehicle segmentation accuracy within the BEV domain. Despite significant advances in sensor technology and multi-sensor fusion, a gap remains in the existing literature regarding the specific effects of camera occlusions on BEV-based perception systems. To address this gap, we use a multi-sensor fusion technique that integrates LiDAR and radar sensor data to mitigate the performance degradation caused by occluded cameras. Our findings demonstrate that this approach significantly enhances the accuracy and robustness of vehicle segmentation tasks, leading to more reliable autonomous driving systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05997v1-abstract-full').style.display = 'none'; document.getElementById('2501.05997v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 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">Accepted form publishing at the Electronic Imaging - Autonomous Vehicles and Machines Conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.04721">arXiv:2501.04721</a> <span> [<a href="https://arxiv.org/pdf/2501.04721">pdf</a>, <a href="https://arxiv.org/format/2501.04721">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> </div> </div> <p class="title is-5 mathjax"> A Shape-Based Functional Index for Objective Assessment of Pediatric Motor Function </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shashwat Kumar</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+A">Arafat Rahman</a>, <a href="/search/cs?searchtype=author&query=Gutierrez%2C+R">Robert Gutierrez</a>, <a href="/search/cs?searchtype=author&query=Livermon%2C+S">Sarah Livermon</a>, <a href="/search/cs?searchtype=author&query=McCrady%2C+A+N">Allison N. McCrady</a>, <a href="/search/cs?searchtype=author&query=Blemker%2C+S">Silvia Blemker</a>, <a href="/search/cs?searchtype=author&query=Scharf%2C+R">Rebecca Scharf</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+A">Anuj Srivastava</a>, <a href="/search/cs?searchtype=author&query=Barnes%2C+L+E">Laura E. Barnes</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="2501.04721v1-abstract-short" style="display: inline;"> Clinical assessments for neuromuscular disorders, such as Spinal Muscular Atrophy (SMA) and Duchenne Muscular Dystrophy (DMD), continue to rely on subjective measures to monitor treatment response and disease progression. We introduce a novel method using wearable sensors to objectively assess motor function during daily activities in 19 patients with DMD, 9 with SMA, and 13 age-matched controls.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04721v1-abstract-full').style.display = 'inline'; document.getElementById('2501.04721v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.04721v1-abstract-full" style="display: none;"> Clinical assessments for neuromuscular disorders, such as Spinal Muscular Atrophy (SMA) and Duchenne Muscular Dystrophy (DMD), continue to rely on subjective measures to monitor treatment response and disease progression. We introduce a novel method using wearable sensors to objectively assess motor function during daily activities in 19 patients with DMD, 9 with SMA, and 13 age-matched controls. Pediatric movement data is complex due to confounding factors such as limb length variations in growing children and variability in movement speed. Our approach uses Shape-based Principal Component Analysis to align movement trajectories and identify distinct kinematic patterns, including variations in motion speed and asymmetry. Both DMD and SMA cohorts have individuals with motor function on par with healthy controls. Notably, patients with SMA showed greater activation of the motion asymmetry pattern. We further combined projections on these principal components with partial least squares (PLS) to identify a covariation mode with a canonical correlation of r = 0.78 (95% CI: [0.34, 0.94]) with muscle fat infiltration, the Brooke score (a motor function score), and age-related degenerative changes, proposing a novel motor function index. This data-driven method can be deployed in home settings, enabling better longitudinal tracking of treatment efficacy for children with neuromuscular disorders. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04721v1-abstract-full').style.display = 'none'; document.getElementById('2501.04721v1-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 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">13 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/2501.02803">arXiv:2501.02803</a> <span> [<a href="https://arxiv.org/pdf/2501.02803">pdf</a>, <a href="https://arxiv.org/format/2501.02803">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yimin Tang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhenghong Yu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Y">Yi Zheng</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+T+K+S">T. K. Satish Kumar</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaoyang Li</a>, <a href="/search/cs?searchtype=author&query=Koenig%2C+S">Sven Koenig</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="2501.02803v1-abstract-short" style="display: inline;"> Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial in autonomous warehouse operations. Lifelong MAPF (L-MAPF), where agents are continuously reassigned new targets upon completing their current tasks, offers a more realistic approximation of real-world warehouse scenarios. While cache storage systems can enhance efficiency and reduce oper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02803v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02803v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02803v1-abstract-full" style="display: none;"> Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial in autonomous warehouse operations. Lifelong MAPF (L-MAPF), where agents are continuously reassigned new targets upon completing their current tasks, offers a more realistic approximation of real-world warehouse scenarios. While cache storage systems can enhance efficiency and reduce operational costs, existing approaches primarily rely on expectations and mathematical models, often without adequately addressing the challenges of multi-robot planning and execution. In this paper, we introduce a novel mechanism called Lifelong MAPF with Cache Mechanism (L-MAPF-CM), which integrates high-level cache storage with low-level path planning. We have involved a new type of map grid called cache for temporary item storage. Additionally, we involved a task assigner (TA) with a locking mechanism to bridge the gap between the new cache grid and L-MAPF algorithm. The TA dynamically allocates target locations to agents based on their status in various scenarios. We evaluated L-MAPF-CM using different cache replacement policies and task distributions. L-MAPF-CM has demonstrated performance improvements particularly with high cache hit rates and smooth traffic conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02803v1-abstract-full').style.display = 'none'; document.getElementById('2501.02803v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <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:2403.13421</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02392">arXiv:2501.02392</a> <span> [<a href="https://arxiv.org/pdf/2501.02392">pdf</a>, <a href="https://arxiv.org/format/2501.02392">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"> Syntactic Evolution in Language Usage </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Surbhit Kumar</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="2501.02392v1-abstract-short" style="display: inline;"> This research aims to investigate the dynamic nature of linguistic style throughout various stages of life, from post teenage to old age. By employing linguistic analysis tools and methodologies, the study will delve into the intricacies of how individuals adapt and modify their language use over time. The research uses a data set of blogs from blogger.com from 2004 and focuses on English for synt… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02392v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02392v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02392v1-abstract-full" style="display: none;"> This research aims to investigate the dynamic nature of linguistic style throughout various stages of life, from post teenage to old age. By employing linguistic analysis tools and methodologies, the study will delve into the intricacies of how individuals adapt and modify their language use over time. The research uses a data set of blogs from blogger.com from 2004 and focuses on English for syntactic analysis. The findings of this research can have implications for linguistics, psychology, and communication studies, shedding light on the intricate relationship between age and language. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02392v1-abstract-full').style.display = 'none'; document.getElementById('2501.02392v1-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 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">4 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.20487">arXiv:2412.20487</a> <span> [<a href="https://arxiv.org/pdf/2412.20487">pdf</a>, <a href="https://arxiv.org/format/2412.20487">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Multimodal Variational Autoencoder: a Barycentric View </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiu%2C+P">Peijie Qiu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wenhui Zhu</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sayantan Kumar</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiwen Chen</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xiaotong Sun</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jin Yang</a>, <a href="/search/cs?searchtype=author&query=Razi%2C+A">Abolfazl Razi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yalin Wang</a>, <a href="/search/cs?searchtype=author&query=Sotiras%2C+A">Aristeidis Sotiras</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="2412.20487v1-abstract-short" style="display: inline;"> Multiple signal modalities, such as vision and sounds, are naturally present in real-world phenomena. Recently, there has been growing interest in learning generative models, in particular variational autoencoder (VAE), to for multimodal representation learning especially in the case of missing modalities. The primary goal of these models is to learn a modality-invariant and modality-specific repr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.20487v1-abstract-full').style.display = 'inline'; document.getElementById('2412.20487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.20487v1-abstract-full" style="display: none;"> Multiple signal modalities, such as vision and sounds, are naturally present in real-world phenomena. Recently, there has been growing interest in learning generative models, in particular variational autoencoder (VAE), to for multimodal representation learning especially in the case of missing modalities. The primary goal of these models is to learn a modality-invariant and modality-specific representation that characterizes information across multiple modalities. Previous attempts at multimodal VAEs approach this mainly through the lens of experts, aggregating unimodal inference distributions with a product of experts (PoE), a mixture of experts (MoE), or a combination of both. In this paper, we provide an alternative generic and theoretical formulation of multimodal VAE through the lens of barycenter. We first show that PoE and MoE are specific instances of barycenters, derived by minimizing the asymmetric weighted KL divergence to unimodal inference distributions. Our novel formulation extends these two barycenters to a more flexible choice by considering different types of divergences. In particular, we explore the Wasserstein barycenter defined by the 2-Wasserstein distance, which better preserves the geometry of unimodal distributions by capturing both modality-specific and modality-invariant representations compared to KL divergence. Empirical studies on three multimodal benchmarks demonstrated the effectiveness of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.20487v1-abstract-full').style.display = 'none'; document.getElementById('2412.20487v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 December, 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">AAAI 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/2412.19512">arXiv:2412.19512</a> <span> [<a href="https://arxiv.org/pdf/2412.19512">pdf</a>, <a href="https://arxiv.org/format/2412.19512">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Farn%2C+H">Hua Farn</a>, <a href="/search/cs?searchtype=author&query=Su%2C+H">Hsuan Su</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S+H">Shachi H Kumar</a>, <a href="/search/cs?searchtype=author&query=Sahay%2C+S">Saurav Sahay</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shang-Tse Chen</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+H">Hung-yi Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.19512v1-abstract-short" style="display: inline;"> Fine-tuning large language models (LLMs) for downstream tasks is a widely adopted approach, but it often leads to safety degradation in safety-aligned LLMs. Currently, many solutions address this issue by incorporating additional safety data, which can be impractical in many cases. In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLM… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19512v1-abstract-full').style.display = 'inline'; document.getElementById('2412.19512v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.19512v1-abstract-full" style="display: none;"> Fine-tuning large language models (LLMs) for downstream tasks is a widely adopted approach, but it often leads to safety degradation in safety-aligned LLMs. Currently, many solutions address this issue by incorporating additional safety data, which can be impractical in many cases. In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLMs without relying on additional safety data? We propose a simple and effective method that maintains the inherent safety of LLMs while enhancing their downstream task performance: merging the weights of pre- and post-fine-tuned safety-aligned models. Experimental results across various downstream tasks, models, and merging methods demonstrate that this approach effectively mitigates safety degradation while improving downstream task performance, offering a practical solution for adapting safety-aligned LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19512v1-abstract-full').style.display = 'none'; document.getElementById('2412.19512v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18771">arXiv:2412.18771</a> <span> [<a href="https://arxiv.org/pdf/2412.18771">pdf</a>, <a href="https://arxiv.org/ps/2412.18771">ps</a>, <a href="https://arxiv.org/format/2412.18771">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"> RIS-Assisted MIMO CV-QKD at THz Frequencies: Channel Estimation and SKR Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sushil Kumar</a>, <a href="/search/cs?searchtype=author&query=Dash%2C+S+P">Soumya P. Dash</a>, <a href="/search/cs?searchtype=author&query=Ghose%2C+D">Debasish Ghose</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="2412.18771v1-abstract-short" style="display: inline;"> In this paper, a multiple-input multiple-output (MIMO) wireless system incorporating a reconfigurable intelligent surface (RIS) to efficiently operate at terahertz (THz) frequencies is considered. The transmitter, Alice, employs continuous-variable quantum key distribution (CV-QKD) to communicate secret keys to the receiver, Bob, which utilizes either homodyne or heterodyne detection. The latter n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18771v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18771v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18771v1-abstract-full" style="display: none;"> In this paper, a multiple-input multiple-output (MIMO) wireless system incorporating a reconfigurable intelligent surface (RIS) to efficiently operate at terahertz (THz) frequencies is considered. The transmitter, Alice, employs continuous-variable quantum key distribution (CV-QKD) to communicate secret keys to the receiver, Bob, which utilizes either homodyne or heterodyne detection. The latter node applies the least-squared approach to estimate the effective MIMO channel gain matrix prior to receiving the secret key, and this estimation is made available to Alice via an error-free feedback channel. An eavesdropper, Eve, is assumed to employ a collective Gaussian entanglement attack on the feedback channel to avail the estimated channel state information. We present a novel closed-form expression for the secret key rate (SKR) performance of the proposed RIS-assisted THz CV-QKD system. The effect of various system parameters, such as the number of RIS elements and their phase configurations, the channel estimation error, and the detector noise, on the SKR performance are studied via numerical evaluation of the derived formula. It is demonstrated that the RIS contributes to larger SKR for larger link distances, and that heterodyne detection is preferable over homodyne at lower pilot symbol powers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18771v1-abstract-full').style.display = 'none'; document.getElementById('2412.18771v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 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">11 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18596">arXiv:2412.18596</a> <span> [<a href="https://arxiv.org/pdf/2412.18596">pdf</a>, <a href="https://arxiv.org/format/2412.18596">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"> LatentCRF: Continuous CRF for Efficient Latent Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ranasinghe%2C+K">Kanchana Ranasinghe</a>, <a href="/search/cs?searchtype=author&query=Jayasumana%2C+S">Sadeep Jayasumana</a>, <a href="/search/cs?searchtype=author&query=Veit%2C+A">Andreas Veit</a>, <a href="/search/cs?searchtype=author&query=Chakrabarti%2C+A">Ayan Chakrabarti</a>, <a href="/search/cs?searchtype=author&query=Glasner%2C+D">Daniel Glasner</a>, <a href="/search/cs?searchtype=author&query=Ryoo%2C+M+S">Michael S Ryoo</a>, <a href="/search/cs?searchtype=author&query=Ramalingam%2C+S">Srikumar Ramalingam</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sanjiv Kumar</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="2412.18596v1-abstract-short" style="display: inline;"> Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability. We introduce LatentCRF, a continuous Conditional Random Field (CRF) model, implemented as a neural network layer, that models the spatial and semantic relationships among the latent vectors in the LDM. By replacing some… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18596v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18596v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18596v1-abstract-full" style="display: none;"> Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability. We introduce LatentCRF, a continuous Conditional Random Field (CRF) model, implemented as a neural network layer, that models the spatial and semantic relationships among the latent vectors in the LDM. By replacing some of the computationally-intensive LDM inference iterations with our lightweight LatentCRF, we achieve a superior balance between quality, speed and diversity. We increase inference efficiency by 33% with no loss in image quality or diversity compared to the full LDM. LatentCRF is an easy add-on, which does not require modifying the LDM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18596v1-abstract-full').style.display = 'none'; document.getElementById('2412.18596v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 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/2412.17823">arXiv:2412.17823</a> <span> [<a href="https://arxiv.org/pdf/2412.17823">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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="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/10.1016/j.heliyon.2024.e39268">10.1016/j.heliyon.2024.e39268 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> RUL forecasting for wind turbine predictive maintenance based on deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+S+S">Syed Shazaib Shah</a>, <a href="/search/cs?searchtype=author&query=Daoliang%2C+T">Tan Daoliang</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S+C">Sah Chandan Kumar</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="2412.17823v1-abstract-short" style="display: inline;"> Predictive maintenance (PdM) is increasingly pursued to reduce wind farm operation and maintenance costs by accurately predicting the remaining useful life (RUL) and strategically scheduling maintenance. However, the remoteness of wind farms often renders current methodologies ineffective, as they fail to provide a sufficiently reliable advance time window for maintenance planning, limiting PdM's… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17823v1-abstract-full').style.display = 'inline'; document.getElementById('2412.17823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.17823v1-abstract-full" style="display: none;"> Predictive maintenance (PdM) is increasingly pursued to reduce wind farm operation and maintenance costs by accurately predicting the remaining useful life (RUL) and strategically scheduling maintenance. However, the remoteness of wind farms often renders current methodologies ineffective, as they fail to provide a sufficiently reliable advance time window for maintenance planning, limiting PdM's practicality. This study introduces a novel deep learning (DL) methodology for future RUL forecasting. By employing a multi-parametric attention-based DL approach that bypasses feature engineering, thereby minimizing the risk of human error, two models: ForeNet-2d and ForeNet-3d are proposed. These models successfully forecast the RUL for seven multifaceted wind turbine (WT) failures with a 2-week forecast window. The most precise forecast deviated by only 10 minutes from the actual RUL, while the least accurate prediction deviated by 1.8 days, with most predictions being off by only a few hours. This methodology offers a substantial time frame to access remote WTs and perform necessary maintenance, thereby enabling the practical implementation of PdM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17823v1-abstract-full').style.display = 'none'; document.getElementById('2412.17823v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 16 figures, Journal Paper</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> Volume 10, Issue 20e39268October 30, 2024 <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 14J60 (Primary) </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Helyion (Journal); Volume 10, Issue 20e39268October 30, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16624">arXiv:2412.16624</a> <span> [<a href="https://arxiv.org/pdf/2412.16624">pdf</a>, <a href="https://arxiv.org/format/2412.16624">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Automated Bleeding Detection and Classification in Wireless Capsule Endoscopy with YOLOv8-X </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shekar%2C+P+C">Pavan C Shekar</a>, <a href="/search/cs?searchtype=author&query=Kanhangad%2C+V">Vivek Kanhangad</a>, <a href="/search/cs?searchtype=author&query=Maheshwari%2C+S">Shishir Maheshwari</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+T+S">T Sunil Kumar</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="2412.16624v1-abstract-short" style="display: inline;"> Gastrointestinal (GI) bleeding, a critical indicator of digestive system disorders, re quires efficient and accurate detection methods. This paper presents our solution to the Auto-WCEBleedGen Version V1 Challenge, where we achieved the consolation position. We developed a unified YOLOv8-X model for both detection and classification of bleeding regions in Wireless Capsule Endoscopy (WCE) images. O… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16624v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16624v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16624v1-abstract-full" style="display: none;"> Gastrointestinal (GI) bleeding, a critical indicator of digestive system disorders, re quires efficient and accurate detection methods. This paper presents our solution to the Auto-WCEBleedGen Version V1 Challenge, where we achieved the consolation position. We developed a unified YOLOv8-X model for both detection and classification of bleeding regions in Wireless Capsule Endoscopy (WCE) images. Our approach achieved 96.10% classification accuracy and 76.8% mean Average Precision (mAP) at 0.5 IoU on the val idation dataset. Through careful dataset curation and annotation, we assembled and trained on 6,345 diverse images to ensure robust model performance. Our implementa tion code and trained models are publicly available at https://github.com/pavan98765/Auto-WCEBleedGen. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16624v1-abstract-full').style.display = 'none'; document.getElementById('2412.16624v1-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 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">11 pages, 4 figures, challenge</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.13578">arXiv:2412.13578</a> <span> [<a href="https://arxiv.org/pdf/2412.13578">pdf</a>, <a href="https://arxiv.org/format/2412.13578">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"> Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shanu Kumar</a>, <a href="/search/cs?searchtype=author&query=Kholkar%2C+G">Gauri Kholkar</a>, <a href="/search/cs?searchtype=author&query=Mendke%2C+S">Saish Mendke</a>, <a href="/search/cs?searchtype=author&query=Sadana%2C+A">Anubhav Sadana</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+P">Parag Agrawal</a>, <a href="/search/cs?searchtype=author&query=Dandapat%2C+S">Sandipan Dandapat</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="2412.13578v1-abstract-short" style="display: inline;"> With the growth of social media and large language models, content moderation has become crucial. Many existing datasets lack adequate representation of different groups, resulting in unreliable assessments. To tackle this, we propose a socio-culturally aware evaluation framework for LLM-driven content moderation and introduce a scalable method for creating diverse datasets using persona-based gen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13578v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13578v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13578v1-abstract-full" style="display: none;"> With the growth of social media and large language models, content moderation has become crucial. Many existing datasets lack adequate representation of different groups, resulting in unreliable assessments. To tackle this, we propose a socio-culturally aware evaluation framework for LLM-driven content moderation and introduce a scalable method for creating diverse datasets using persona-based generation. Our analysis reveals that these datasets provide broader perspectives and pose greater challenges for LLMs than diversity-focused generation methods without personas. This challenge is especially pronounced in smaller LLMs, emphasizing the difficulties they encounter in moderating such diverse content. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13578v1-abstract-full').style.display = 'none'; document.getElementById('2412.13578v1-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 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 in SUMEval Workshop in 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/2412.11474">arXiv:2412.11474</a> <span> [<a href="https://arxiv.org/pdf/2412.11474">pdf</a>, <a href="https://arxiv.org/format/2412.11474">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Noise-Resilient Homomorphic Encryption: A Framework for Secure Data Processing in Health care Domain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shuriya%2C+B">B. Shuriya</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S+V">S. Vimal Kumar</a>, <a href="/search/cs?searchtype=author&query=Bagyalakshmi%2C+K">K. Bagyalakshmi</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="2412.11474v1-abstract-short" style="display: inline;"> In this paper, we introduce the Fully Homomorphic Integrity Model (HIM), a novel approach designed to enhance security, efficiency, and reliability in encrypted data processing, primarily within the health care industry. HIM addresses the key challenges that noise accumulation, computational overheads, and data integrity pose during homomorphic operations. Our contribution of HIM: advances in nois… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11474v1-abstract-full').style.display = 'inline'; document.getElementById('2412.11474v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.11474v1-abstract-full" style="display: none;"> In this paper, we introduce the Fully Homomorphic Integrity Model (HIM), a novel approach designed to enhance security, efficiency, and reliability in encrypted data processing, primarily within the health care industry. HIM addresses the key challenges that noise accumulation, computational overheads, and data integrity pose during homomorphic operations. Our contribution of HIM: advances in noise management through the rational number adjustment; key generation based on personalized prime numbers; and time complexity analysis details for key operations. In HIM, some additional mechanisms were introduced, including robust mechanisms of decryption. Indeed, the decryption mechanism ensures that the data recovered upon doing complex homomorphic computation will be valid and reliable. The healthcare id model is tested, and it supports real-time processing of data with privacy maintained concerning patients. It supports analytics and decision-making processes without any compromise on the integrity of information concerning patients. Output HIM promotes the efficiency of encryption to a greater extent as it reduces the encryption time up to 35ms and decryption time up to 140ms, which is better when compared to other models in the existence. Ciphertext size also becomes the smallest one, which is 4KB. Our experiments confirm that HIM is indeed a very efficient and secure privacy-preserving solution for healthcare applications <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11474v1-abstract-full').style.display = 'none'; document.getElementById('2412.11474v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <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">Confirmed</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.11384">arXiv:2412.11384</a> <span> [<a href="https://arxiv.org/pdf/2412.11384">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> A Comprehensive Review of Adversarial Attacks on Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ahmed%2C+S+Q">Syed Quiser Ahmed</a>, <a href="/search/cs?searchtype=author&query=Ganesh%2C+B+V">Bharathi Vokkaliga Ganesh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S+S">Sathyanarayana Sampath Kumar</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+P">Prakhar Mishra</a>, <a href="/search/cs?searchtype=author&query=Anand%2C+R">Ravi Anand</a>, <a href="/search/cs?searchtype=author&query=Akurathi%2C+B">Bhanuteja Akurathi</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="2412.11384v1-abstract-short" style="display: inline;"> This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and future research directions. To gain practical insights, we employ the Adversarial Robustness Toolbox (ART) [1] library to simulate these attacks on real-world use c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11384v1-abstract-full').style.display = 'inline'; document.getElementById('2412.11384v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.11384v1-abstract-full" style="display: none;"> This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and future research directions. To gain practical insights, we employ the Adversarial Robustness Toolbox (ART) [1] library to simulate these attacks on real-world use cases, such as self-driving cars. Our goal is to inform practitioners and researchers about the challenges and opportunities in defending AI systems against adversarial threats. By providing a comprehensive comparison of different attack methods, we aim to contribute to the development of more robust and secure AI systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11384v1-abstract-full').style.display = 'none'; document.getElementById('2412.11384v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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/2412.09935">arXiv:2412.09935</a> <span> [<a href="https://arxiv.org/pdf/2412.09935">pdf</a>, <a href="https://arxiv.org/format/2412.09935">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> SCRUBD: Smart Contracts Reentrancy and Unhandled Exceptions Vulnerability Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yashavant%2C+C+S">Chavhan Sujeet Yashavant</a>, <a href="/search/cs?searchtype=author&query=Chavda%2C+M">MitrajSinh Chavda</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Saurabh Kumar</a>, <a href="/search/cs?searchtype=author&query=Karkare%2C+A">Amey Karkare</a>, <a href="/search/cs?searchtype=author&query=Karmakar%2C+A">Angshuman Karmakar</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="2412.09935v1-abstract-short" style="display: inline;"> Smart Contracts (SCs) handle transactions in the Ethereum blockchain worth millions of United States dollars, making them a lucrative target for attackers seeking to exploit vulnerabilities and steal funds. The Ethereum community has developed a rich set of tools to detect vulnerabilities in SCs, including reentrancy (RE) and unhandled exceptions (UX). A dataset of SCs labelled with vulnerabilitie… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09935v1-abstract-full').style.display = 'inline'; document.getElementById('2412.09935v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.09935v1-abstract-full" style="display: none;"> Smart Contracts (SCs) handle transactions in the Ethereum blockchain worth millions of United States dollars, making them a lucrative target for attackers seeking to exploit vulnerabilities and steal funds. The Ethereum community has developed a rich set of tools to detect vulnerabilities in SCs, including reentrancy (RE) and unhandled exceptions (UX). A dataset of SCs labelled with vulnerabilities is needed to evaluate the tools' efficacy. Existing SC datasets with labelled vulnerabilities have limitations, such as covering only a limited range of vulnerability scenarios and containing incorrect labels. As a result, there is a lack of a standardized dataset to compare the performances of these tools. SCRUBD aims to fill this gap. We present a dataset of real-world SCs and synthesized SCs labelled with RE and UX. The real-world SC dataset is labelled through crowdsourcing, followed by manual inspection by an expert, and covers both RE and UX vulnerabilities. On the other hand, the synthesized dataset is carefully crafted to cover various RE scenarios only. Using SCRUBD we compared the performance of six popular vulnerability detection tools. Based on our study, we found that Slither outperforms other tools on a crowdsourced dataset in detecting RE vulnerabilities, while Sailfish outperforms other tools on a manually synthesized dataset for detecting RE. For UX vulnerabilities, Slither outperforms all other tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09935v1-abstract-full').style.display = 'none'; document.getElementById('2412.09935v1-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">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">7 pages, 2 figures, 3 tables, 2 code listings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.09831">arXiv:2412.09831</a> <span> [<a href="https://arxiv.org/pdf/2412.09831">pdf</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"> Ensemble Classification-Based Spectrum Sensing Using Support Vector Machine for CRN </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=Singh%2C+R">Raj Singh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sandeep Kumar</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="2412.09831v1-abstract-short" style="display: inline;"> As the demand for internet of things (IoT) and device-to-device (D2D) applications in next generation communication systems increases, we are confronted with a challenge of spectrum scarcity. One promising solution to this problem is cognitive radio network (CRN), where the key element is the spectrum - a valuable and sharable natural resource that should not be wasted. To design efficient and sus… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09831v1-abstract-full').style.display = 'inline'; document.getElementById('2412.09831v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.09831v1-abstract-full" style="display: none;"> As the demand for internet of things (IoT) and device-to-device (D2D) applications in next generation communication systems increases, we are confronted with a challenge of spectrum scarcity. One promising solution to this problem is cognitive radio network (CRN), where the key element is the spectrum - a valuable and sharable natural resource that should not be wasted. To design efficient and sustainable networks for the future, it is crucial to ensure that spectrum sensing is not only accurate and rapid, but also energy-efficient. Spectrum sensing is a critical aspect of CRNs, and this study is mainly focused on it. In this research, we employ the supervised machine learning algorithm, support vector machine (SVM), to detect primary users (PU). We investigate different variants of SVM, including linear, polynomial, and Gaussian radial basic function (RBF), and employ an ensemble classification-based approach to improve the classifier's performance and productivity. The simulation results demonstrate that the ensemble classifier achieves the highest performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09831v1-abstract-full').style.display = 'none'; document.getElementById('2412.09831v1-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 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/2412.09789">arXiv:2412.09789</a> <span> [<a href="https://arxiv.org/pdf/2412.09789">pdf</a>, <a href="https://arxiv.org/format/2412.09789">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Sonal Kumar</a>, <a href="/search/cs?searchtype=author&query=Seetharaman%2C+P">Prem Seetharaman</a>, <a href="/search/cs?searchtype=author&query=Salamon%2C+J">Justin Salamon</a>, <a href="/search/cs?searchtype=author&query=Manocha%2C+D">Dinesh Manocha</a>, <a href="/search/cs?searchtype=author&query=Nieto%2C+O">Oriol Nieto</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="2412.09789v1-abstract-short" style="display: inline;"> The field of text-to-audio generation has seen significant advancements, and yet the ability to finely control the acoustic characteristics of generated audio remains under-explored. In this paper, we introduce a novel yet simple approach to generate sound effects with control over key acoustic parameters such as loudness, pitch, reverb, fade, brightness, noise and duration, enabling creative appl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09789v1-abstract-full').style.display = 'inline'; document.getElementById('2412.09789v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.09789v1-abstract-full" style="display: none;"> The field of text-to-audio generation has seen significant advancements, and yet the ability to finely control the acoustic characteristics of generated audio remains under-explored. In this paper, we introduce a novel yet simple approach to generate sound effects with control over key acoustic parameters such as loudness, pitch, reverb, fade, brightness, noise and duration, enabling creative applications in sound design and content creation. These parameters extend beyond traditional Digital Signal Processing (DSP) techniques, incorporating learned representations that capture the subtleties of how sound characteristics can be shaped in context, enabling a richer and more nuanced control over the generated audio. Our approach is model-agnostic and is based on learning the disentanglement between audio semantics and its acoustic features. Our approach not only enhances the versatility and expressiveness of text-to-audio generation but also opens new avenues for creative audio production and sound design. Our objective and subjective evaluation results demonstrate the effectiveness of our approach in producing high-quality, customizable audio outputs that align closely with user specifications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09789v1-abstract-full').style.display = 'none'; document.getElementById('2412.09789v1-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 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">Website: https://sonalkum.github.io/SILA/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.08992">arXiv:2412.08992</a> <span> [<a href="https://arxiv.org/pdf/2412.08992">pdf</a>, <a href="https://arxiv.org/format/2412.08992">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Benchmarking of GPU-optimized Quantum-Inspired Evolutionary Optimization Algorithm using Functional Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+K+E+S">Kandula Eswara Sai Kumar</a>, <a href="/search/cs?searchtype=author&query=S%2C+S+B">Supreeth B S</a>, <a href="/search/cs?searchtype=author&query=Dalvi%2C+R">Rajas Dalvi</a>, <a href="/search/cs?searchtype=author&query=Mittal%2C+A">Aman Mittal</a>, <a href="/search/cs?searchtype=author&query=Akhtar%2C+A">Aakif Akhtar</a>, <a href="/search/cs?searchtype=author&query=Bosco%2C+F+D">Ferdin Don Bosco</a>, <a href="/search/cs?searchtype=author&query=Lineswala%2C+R">Rut Lineswala</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+A">Abhishek Chopra</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="2412.08992v1-abstract-short" style="display: inline;"> This article presents a comparative analysis of GPU-parallelized implementations of the quantum-inspired evolutionary optimization (QIEO) approach and one of the well-known classical metaheuristic techniques, the genetic algorithm (GA). The study assesses the performance of both algorithms on highly non-linear, non-convex, and non-separable function optimization problems, viz., Ackley, Rosenbrock,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08992v1-abstract-full').style.display = 'inline'; document.getElementById('2412.08992v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.08992v1-abstract-full" style="display: none;"> This article presents a comparative analysis of GPU-parallelized implementations of the quantum-inspired evolutionary optimization (QIEO) approach and one of the well-known classical metaheuristic techniques, the genetic algorithm (GA). The study assesses the performance of both algorithms on highly non-linear, non-convex, and non-separable function optimization problems, viz., Ackley, Rosenbrock, and Rastrigin, that are representative of the complex real-world optimization problems. The performance of these algorithms is checked by varying the population sizes by keeping all other parameters constant and comparing the fitness value it reached along with the number of function evaluations they required for convergence. The results demonstrate that QIEO performs better for these functions than GA, by achieving the target fitness with fewer function evaluations and significantly reducing the total optimization time approximately three times for the Ackley function and four times for the Rosenbrock and Rastrigin functions. Furthermore, QIEO exhibits greater consistency across trials, with a steady convergence rate that leads to a more uniform number of function evaluations, highlighting its reliability in solving challenging optimization problems. The findings indicate that QIEO is a promising alternative to GA for these kind of functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08992v1-abstract-full').style.display = 'none'; document.getElementById('2412.08992v1-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 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/2412.07415">arXiv:2412.07415</a> <span> [<a href="https://arxiv.org/pdf/2412.07415">pdf</a>, <a href="https://arxiv.org/format/2412.07415">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="Computers and Society">cs.CY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/I2CT61223.2024.10544243">10.1109/I2CT61223.2024.10544243 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Machine Learning Algorithms for Detecting Mental Stress in College Students </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Ashutosh Singh</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+K">Khushdeep Singh</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+A">Amit Kumar</a>, <a href="/search/cs?searchtype=author&query=Shrivastava%2C+A">Abhishek Shrivastava</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Santosh Kumar</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="2412.07415v1-abstract-short" style="display: inline;"> In today's world, stress is a big problem that affects people's health and happiness. More and more people are feeling stressed out, which can lead to lots of health issues like breathing problems, feeling overwhelmed, heart attack, diabetes, etc. This work endeavors to forecast stress and non-stress occurrences among college students by applying various machine learning algorithms: Decision Trees… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07415v1-abstract-full').style.display = 'inline'; document.getElementById('2412.07415v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.07415v1-abstract-full" style="display: none;"> In today's world, stress is a big problem that affects people's health and happiness. More and more people are feeling stressed out, which can lead to lots of health issues like breathing problems, feeling overwhelmed, heart attack, diabetes, etc. This work endeavors to forecast stress and non-stress occurrences among college students by applying various machine learning algorithms: Decision Trees, Random Forest, Support Vector Machines, AdaBoost, Naive Bayes, Logistic Regression, and K-nearest Neighbors. The primary objective of this work is to leverage a research study to predict and mitigate stress and non-stress based on the collected questionnaire dataset. We conducted a workshop with the primary goal of studying the stress levels found among the students. This workshop was attended by Approximately 843 students aged between 18 to 21 years old. A questionnaire was given to the students validated under the guidance of the experts from the All India Institute of Medical Sciences (AIIMS) Raipur, Chhattisgarh, India, on which our dataset is based. The survey consists of 28 questions, aiming to comprehensively understand the multidimensional aspects of stress, including emotional well-being, physical health, academic performance, relationships, and leisure. This work finds that Support Vector Machines have a maximum accuracy for Stress, reaching 95\%. The study contributes to a deeper understanding of stress determinants. It aims to improve college student's overall quality of life and academic success, addressing the multifaceted nature of stress. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07415v1-abstract-full').style.display = 'none'; document.getElementById('2412.07415v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper was presented at an IEEE conference and is 5 pages long with 5 figures. It discusses machine learning algorithms for detecting mental stress in college students</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 9th International Conference for Convergence in Technology (I2CT) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.06603">arXiv:2412.06603</a> <span> [<a href="https://arxiv.org/pdf/2412.06603">pdf</a>, <a href="https://arxiv.org/format/2412.06603">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprise </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weisz%2C+J+D">Justin D. Weisz</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Shraddha Kumar</a>, <a href="/search/cs?searchtype=author&query=Muller%2C+M">Michael Muller</a>, <a href="/search/cs?searchtype=author&query=Browne%2C+K">Karen-Ellen Browne</a>, <a href="/search/cs?searchtype=author&query=Goldberg%2C+A">Arielle Goldberg</a>, <a href="/search/cs?searchtype=author&query=Heintze%2C+E">Ellice Heintze</a>, <a href="/search/cs?searchtype=author&query=Bajpai%2C+S">Shagun Bajpai</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="2412.06603v1-abstract-short" style="display: inline;"> AI assistants are being created to help software engineers conduct a variety of coding-related tasks, such as writing, documenting, and testing code. We describe the use of the watsonx Code Assistant (WCA), an LLM-powered coding assistant deployed internally within IBM. Through surveys of two user cohorts (N=669) and unmoderated usability testing (N=15), we examined developers' experiences with WC… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06603v1-abstract-full').style.display = 'inline'; document.getElementById('2412.06603v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.06603v1-abstract-full" style="display: none;"> AI assistants are being created to help software engineers conduct a variety of coding-related tasks, such as writing, documenting, and testing code. We describe the use of the watsonx Code Assistant (WCA), an LLM-powered coding assistant deployed internally within IBM. Through surveys of two user cohorts (N=669) and unmoderated usability testing (N=15), we examined developers' experiences with WCA and its impact on their productivity. We learned about their motivations for using (or not using) WCA, we examined their expectations of its speed and quality, and we identified new considerations regarding ownership of and responsibility for generated code. Our case study characterizes the impact of an LLM-powered assistant on developers' perceptions of productivity and it shows that although such tools do often provide net productivity increases, these benefits may not always be experienced by all users. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06603v1-abstract-full').style.display = 'none'; document.getElementById('2412.06603v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages, 3 figures. To be published in CHI EA 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/2412.05208">arXiv:2412.05208</a> <span> [<a href="https://arxiv.org/pdf/2412.05208">pdf</a>, <a href="https://arxiv.org/format/2412.05208">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> </div> </div> <p class="title is-5 mathjax"> A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Aditi Singh</a>, <a href="/search/cs?searchtype=author&query=Shetty%2C+A">Akash Shetty</a>, <a href="/search/cs?searchtype=author&query=Ehtesham%2C+A">Abul Ehtesham</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Saket Kumar</a>, <a href="/search/cs?searchtype=author&query=Khoei%2C+T+T">Tala Talaei Khoei</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="2412.05208v2-abstract-short" style="display: inline;"> Text-to-SQL systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (SQL), bridging the gap between non-technical users and complex database management systems. This survey provides a comprehensive overview of the evolution of AI-driven text-to-SQL systems, highlighting their foundational components, advancements in large language… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05208v2-abstract-full').style.display = 'inline'; document.getElementById('2412.05208v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05208v2-abstract-full" style="display: none;"> Text-to-SQL systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (SQL), bridging the gap between non-technical users and complex database management systems. This survey provides a comprehensive overview of the evolution of AI-driven text-to-SQL systems, highlighting their foundational components, advancements in large language model (LLM) architectures, and the critical role of datasets such as Spider, WikiSQL, and CoSQL in driving progress. We examine the applications of text-to-SQL in domains like healthcare, education, and finance, emphasizing their transformative potential for improving data accessibility. Additionally, we analyze persistent challenges, including domain generalization, query optimization, support for multi-turn conversational interactions, and the limited availability of datasets tailored for NoSQL databases and dynamic real-world scenarios. To address these challenges, we outline future research directions, such as extending text-to-SQL capabilities to support NoSQL databases, designing datasets for dynamic multi-turn interactions, and optimizing systems for real-world scalability and robustness. By surveying current advancements and identifying key gaps, this paper aims to guide the next generation of research and applications in LLM-based text-to-SQL systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05208v2-abstract-full').style.display = 'none'; document.getElementById('2412.05208v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04782">arXiv:2412.04782</a> <span> [<a href="https://arxiv.org/pdf/2412.04782">pdf</a>, <a href="https://arxiv.org/format/2412.04782">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="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Aditi Singh</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+N+P">Nirmal Prakashbhai Patel</a>, <a href="/search/cs?searchtype=author&query=Ehtesham%2C+A">Abul Ehtesham</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Saket Kumar</a>, <a href="/search/cs?searchtype=author&query=Khoei%2C+T+T">Tala Talaei Khoei</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="2412.04782v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have transformed numerous domains by providing advanced capabilities in natural language understanding, generation, and reasoning. Despite their groundbreaking applications across industries such as research, healthcare, and creative media, their rapid adoption raises critical concerns regarding sustainability. This survey paper comprehensively examines the environment… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04782v2-abstract-full').style.display = 'inline'; document.getElementById('2412.04782v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04782v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have transformed numerous domains by providing advanced capabilities in natural language understanding, generation, and reasoning. Despite their groundbreaking applications across industries such as research, healthcare, and creative media, their rapid adoption raises critical concerns regarding sustainability. This survey paper comprehensively examines the environmental, economic, and computational challenges associated with LLMs, focusing on energy consumption, carbon emissions, and resource utilization in data centers. By synthesizing insights from existing literature, this work explores strategies such as resource-efficient training, sustainable deployment practices, and lifecycle assessments to mitigate the environmental impacts of LLMs. Key areas of emphasis include energy optimization, renewable energy integration, and balancing performance with sustainability. The findings aim to guide researchers, practitioners, and policymakers in developing actionable strategies for sustainable AI systems, fostering a responsible and environmentally conscious future for artificial intelligence. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04782v2-abstract-full').style.display = 'none'; document.getElementById('2412.04782v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03837">arXiv:2412.03837</a> <span> [<a href="https://arxiv.org/pdf/2412.03837">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Movie Gen: SWOT Analysis of Meta's Generative AI Foundation Model for Transforming Media Generation, Advertising, and Entertainment Industries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ehtesham%2C+A">Abul Ehtesham</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Saket Kumar</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Aditi Singh</a>, <a href="/search/cs?searchtype=author&query=Khoei%2C+T+T">Tala Talaei Khoei</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="2412.03837v1-abstract-short" style="display: inline;"> Generative AI is reshaping the media landscape, enabling unprecedented capabilities in video creation, personalization, and scalability. This paper presents a comprehensive SWOT analysis of Metas Movie Gen, a cutting-edge generative AI foundation model designed to produce 1080p HD videos with synchronized audio from simple text prompts. We explore its strengths, including high-resolution video gen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03837v1-abstract-full').style.display = 'inline'; document.getElementById('2412.03837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03837v1-abstract-full" style="display: none;"> Generative AI is reshaping the media landscape, enabling unprecedented capabilities in video creation, personalization, and scalability. This paper presents a comprehensive SWOT analysis of Metas Movie Gen, a cutting-edge generative AI foundation model designed to produce 1080p HD videos with synchronized audio from simple text prompts. We explore its strengths, including high-resolution video generation, precise editing, and seamless audio integration, which make it a transformative tool across industries such as filmmaking, advertising, and education. However, the analysis also addresses limitations, such as constraints on video length and potential biases in generated content, which pose challenges for broader adoption. In addition, we examine the evolving regulatory and ethical considerations surrounding generative AI, focusing on issues like content authenticity, cultural representation, and responsible use. Through comparative insights with leading models like DALL-E and Google Imagen, this paper highlights Movie Gens unique features, such as video personalization and multimodal synthesis, while identifying opportunities for innovation and areas requiring further research. Our findings provide actionable insights for stakeholders, emphasizing both the opportunities and challenges of deploying generative AI in media production. This work aims to guide future advancements in generative AI, ensuring scalability, quality, and ethical integrity in this rapidly evolving field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03837v1-abstract-full').style.display = 'none'; document.getElementById('2412.03837v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </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=Kumar%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Kumar%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