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 86 results for author: <span class="mathjax">Sharma, H</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=Sharma%2C+H">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="Sharma, H"> </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=Sharma%2C+H&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="Sharma, H"> <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=Sharma%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sharma%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sharma%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13333">arXiv:2502.13333</a> <span> [<a href="https://arxiv.org/pdf/2502.13333">pdf</a>, <a href="https://arxiv.org/format/2502.13333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> An Uncertainty-Aware Data-Driven Predictive Controller for Hybrid Power Plants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Desai%2C+M">Manavendra Desai</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Glavaski%2C+S">Sonja Glavaski</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.13333v1-abstract-short" style="display: inline;"> Given the advancements in data-driven modeling for complex engineering and scientific applications, this work utilizes a data-driven predictive control method, namely subspace predictive control, to coordinate hybrid power plant components and meet a desired power demand despite the presence of weather uncertainties. An uncertainty-aware data-driven predictive controller is proposed, and its poten… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13333v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13333v1-abstract-full" style="display: none;"> Given the advancements in data-driven modeling for complex engineering and scientific applications, this work utilizes a data-driven predictive control method, namely subspace predictive control, to coordinate hybrid power plant components and meet a desired power demand despite the presence of weather uncertainties. An uncertainty-aware data-driven predictive controller is proposed, and its potential is analyzed using real-world electricity demand profiles. For the analysis, a hybrid power plant with wind, solar, and co-located energy storage capacity of 4 MW each is considered. The analysis shows that the predictive controller can track a real-world-inspired electricity demand profile despite the presence of weather-induced uncertainties and be an intelligent forecaster for HPP performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13333v1-abstract-full').style.display = 'none'; document.getElementById('2502.13333v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11362">arXiv:2411.11362</a> <span> [<a href="https://arxiv.org/pdf/2411.11362">pdf</a>, <a href="https://arxiv.org/format/2411.11362">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Salvatelli%2C+V">Valentina Salvatelli</a>, <a href="/search/cs?searchtype=author&query=Srivastav%2C+S">Shaury Srivastav</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Ilse%2C+M">Maximilian Ilse</a>, <a href="/search/cs?searchtype=author&query=Bond-Taylor%2C+S">Sam Bond-Taylor</a>, <a href="/search/cs?searchtype=author&query=Ranjit%2C+M+P">Mercy Prasanna Ranjit</a>, <a href="/search/cs?searchtype=author&query=Falck%2C+F">Fabian Falck</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Richardson%2C+H">Hannah Richardson</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria Teodora Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S+L">Stephanie L. Hyland</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11362v1-abstract-short" style="display: inline;"> There is growing interest in applying AI to radiology report generation, particularly for chest X-rays (CXRs). This paper investigates whether incorporating pixel-level information through segmentation masks can improve fine-grained image interpretation of multimodal large language models (MLLMs) for radiology report generation. We introduce MAIRA-Seg, a segmentation-aware MLLM framework designed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11362v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11362v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11362v1-abstract-full" style="display: none;"> There is growing interest in applying AI to radiology report generation, particularly for chest X-rays (CXRs). This paper investigates whether incorporating pixel-level information through segmentation masks can improve fine-grained image interpretation of multimodal large language models (MLLMs) for radiology report generation. We introduce MAIRA-Seg, a segmentation-aware MLLM framework designed to utilize semantic segmentation masks alongside CXRs for generating radiology reports. We train expert segmentation models to obtain mask pseudolabels for radiology-specific structures in CXRs. Subsequently, building on the architectures of MAIRA, a CXR-specialised model for report generation, we integrate a trainable segmentation tokens extractor that leverages these mask pseudolabels, and employ mask-aware prompting to generate draft radiology reports. Our experiments on the publicly available MIMIC-CXR dataset show that MAIRA-Seg outperforms non-segmentation baselines. We also investigate set-of-marks prompting with MAIRA and find that MAIRA-Seg consistently demonstrates comparable or superior performance. The results confirm that using segmentation masks enhances the nuanced reasoning of MLLMs, potentially contributing to better clinical outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11362v1-abstract-full').style.display = 'none'; document.getElementById('2411.11362v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted as Proceedings Paper at ML4H 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.24096">arXiv:2410.24096</a> <span> [<a href="https://arxiv.org/pdf/2410.24096">pdf</a>, <a href="https://arxiv.org/format/2410.24096">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="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Omi%2C+N">Nabil Omi</a>, <a href="/search/cs?searchtype=author&query=Hasanbeig%2C+H">Hosein Hasanbeig</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Rajamani%2C+S+K">Sriram K. Rajamani</a>, <a href="/search/cs?searchtype=author&query=Sen%2C+S">Siddhartha Sen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.24096v1-abstract-short" style="display: inline;"> In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a sense of safety that is carried over from task to task. We model this as a meta-learning process where each task is synchronized with a safeguard that monitors saf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24096v1-abstract-full').style.display = 'inline'; document.getElementById('2410.24096v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.24096v1-abstract-full" style="display: none;"> In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a sense of safety that is carried over from task to task. We model this as a meta-learning process where each task is synchronized with a safeguard that monitors safety and provides a reward signal to the agent. The safeguard is implemented as a finite-state machine based on a safety specification; the reward signal is formally shaped around this specification. The safety specification and its corresponding safeguard can be arbitrarily complex and non-Markovian, which adds flexibility to the training process and explainability to the learned policy. The design of the safeguard is manual but it is high-level and model-agnostic, which gives rise to an end-to-end safe learning approach with wide applicability, from pixel-level game control to language model fine-tuning. Starting from a given set of safety specifications (tasks), we train a model such that it can adapt to new specifications using only a small number of training samples. This is made possible by our method for efficiently transferring safety bias between tasks, which effectively minimizes the number of safety violations. We evaluate our framework in a Minecraft-inspired Gridworld, a VizDoom game environment, and an LLM fine-tuning application. Agents trained with our approach achieve near-minimal safety violations, while baselines are shown to underperform. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24096v1-abstract-full').style.display = 'none'; document.getElementById('2410.24096v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09188">arXiv:2410.09188</a> <span> [<a href="https://arxiv.org/pdf/2410.09188">pdf</a>, <a href="https://arxiv.org/format/2410.09188">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> MFIT: Multi-Fidelity Thermal Modeling for 2.5D and 3D Multi-Chiplet Architectures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pfromm%2C+L">Lukas Pfromm</a>, <a href="/search/cs?searchtype=author&query=Kanani%2C+A">Alish Kanani</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Solanki%2C+P">Parth Solanki</a>, <a href="/search/cs?searchtype=author&query=Tervo%2C+E">Eric Tervo</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jaehyun Park</a>, <a href="/search/cs?searchtype=author&query=Doppa%2C+J+R">Janardhan Rao Doppa</a>, <a href="/search/cs?searchtype=author&query=Pande%2C+P+P">Partha Pratim Pande</a>, <a href="/search/cs?searchtype=author&query=Ogras%2C+U+Y">Umit Y. Ogras</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.09188v3-abstract-short" style="display: inline;"> Rapidly evolving artificial intelligence and machine learning applications require ever-increasing computational capabilities, while monolithic 2D design technologies approach their limits. Heterogeneous integration of smaller chiplets using a 2.5D silicon interposer and 3D packaging has emerged as a promising paradigm to address this limit and meet performance demands. These approaches offer a si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09188v3-abstract-full').style.display = 'inline'; document.getElementById('2410.09188v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09188v3-abstract-full" style="display: none;"> Rapidly evolving artificial intelligence and machine learning applications require ever-increasing computational capabilities, while monolithic 2D design technologies approach their limits. Heterogeneous integration of smaller chiplets using a 2.5D silicon interposer and 3D packaging has emerged as a promising paradigm to address this limit and meet performance demands. These approaches offer a significant cost reduction and higher manufacturing yield than monolithic 2D integrated circuits. However, the compact arrangement and high compute density exacerbate the thermal management challenges, potentially compromising performance. Addressing these thermal modeling challenges is critical, especially as system sizes grow and different design stages require varying levels of accuracy and speed. Since no single thermal modeling technique meets all these needs, this paper introduces MFIT, a range of multi-fidelity thermal models that effectively balance accuracy and speed. These multi-fidelity models can enable efficient design space exploration and runtime thermal management. Our extensive testing on systems with 16, 36, and 64 2.5D integrated chiplets and 16x3 3D integrated chiplets demonstrates that these models can reduce execution times from days to mere seconds and milliseconds with negligible loss in accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09188v3-abstract-full').style.display = 'none'; document.getElementById('2410.09188v3-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">v1</span> submitted 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint for MFIT: Multi-Fidelity Thermal Modeling for 2.5D and 3D Multi-Chiplet Architectures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06576">arXiv:2410.06576</a> <span> [<a href="https://arxiv.org/pdf/2410.06576">pdf</a>, <a href="https://arxiv.org/format/2410.06576">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"> On The Relationship between Visual Anomaly-free and Anomalous Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sadrani%2C+R">Riya Sadrani</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hrishikesh Sharma</a>, <a href="/search/cs?searchtype=author&query=Bachan%2C+A">Ayush Bachan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.06576v1-abstract-short" style="display: inline;"> Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly Detection task assumes the presence of multiple specific anomaly classes e.g. cracks, rusting etc., unlike one-class classification model of past. However, buil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06576v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06576v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06576v1-abstract-full" style="display: none;"> Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly Detection task assumes the presence of multiple specific anomaly classes e.g. cracks, rusting etc., unlike one-class classification model of past. However, building a deep learning model in such setup remains a challenge because anomalies arise rarely, and hence anomaly samples are quite scarce. Transfer learning has been a preferred paradigm in such situations. But the typical source domains with large dataset sizes e.g. ImageNet, JFT-300M, LAION-2B do not correlate well with the domain of surfaces and materials, an important premise of transfer learning. In this paper, we make an important hypothesis and show, by exhaustive experimentation, that the space of anomaly-free visual patterns of the normal samples correlates well with each of the various spaces of anomalous patterns of the class-specific anomaly samples. The first results of using this hypothesis in transfer learning have indeed been quite encouraging. We expect that finding such a simple closeby domain that readily entails large number of samples, and which also oftentimes shows interclass separability though with narrow margins, will be a useful discovery. Especially, it is expected to improve domain adaptation for anomaly detection, and few-shot learning for anomaly detection, making in-the-wild anomaly detection realistically possible in future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06576v1-abstract-full').style.display = 'none'; document.getElementById('2410.06576v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17994">arXiv:2409.17994</a> <span> [<a href="https://arxiv.org/pdf/2409.17994">pdf</a>, <a href="https://arxiv.org/format/2409.17994">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"> CRoP: Context-wise Robust Static Human-Sensing Personalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kaur%2C+S">Sawinder Kaur</a>, <a href="/search/cs?searchtype=author&query=Gump%2C+A">Avery Gump</a>, <a href="/search/cs?searchtype=author&query=Xin%2C+J">Jingyu Xin</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yi Xiao</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshit Sharma</a>, <a href="/search/cs?searchtype=author&query=Benway%2C+N+R">Nina R Benway</a>, <a href="/search/cs?searchtype=author&query=Preston%2C+J+L">Jonathan L Preston</a>, <a href="/search/cs?searchtype=author&query=Salekin%2C+A">Asif Salekin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17994v4-abstract-short" style="display: inline;"> The advancement in deep learning and internet-of-things have led to diverse human sensing applications. However, distinct patterns in human sensing, influenced by various factors or contexts, challenge the generic neural network model's performance due to natural distribution shifts. To address this, personalization tailors models to individual users. Yet most personalization studies overlook intr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17994v4-abstract-full').style.display = 'inline'; document.getElementById('2409.17994v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17994v4-abstract-full" style="display: none;"> The advancement in deep learning and internet-of-things have led to diverse human sensing applications. However, distinct patterns in human sensing, influenced by various factors or contexts, challenge the generic neural network model's performance due to natural distribution shifts. To address this, personalization tailors models to individual users. Yet most personalization studies overlook intra-user heterogeneity across contexts in sensory data, limiting intra-user generalizability. This limitation is especially critical in clinical applications, where limited data availability hampers both generalizability and personalization. Notably, intra-user sensing attributes are expected to change due to external factors such as treatment progression, further complicating the challenges. To address the intra-user generalization challenge, this work introduces CRoP, a novel static personalization approach. CRoP leverages off-the-shelf pre-trained models as generic starting points and captures user-specific traits through adaptive pruning on a minimal sub-network while preserving generic knowledge in the remaining parameters. CRoP demonstrates superior personalization effectiveness and intra-user robustness across four human-sensing datasets, including two from real-world health domains, underscoring its practical and social impact. Additionally, to support CRoP's generalization ability and design choices, we provide empirical justification through gradient inner product analysis, ablation studies, and comparisons against state-of-the-art baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17994v4-abstract-full').style.display = 'none'; document.getElementById('2409.17994v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">33 pages, 6 figues and 12 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/2409.13713">arXiv:2409.13713</a> <span> [<a href="https://arxiv.org/pdf/2409.13713">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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/10.3390/bdcc8090112">10.3390/bdcc8090112 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Sentiment Informed Sentence BERT-Ensemble Algorithm for Depression Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ogunleye%2C+B">Bayode Ogunleye</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemlata Sharma</a>, <a href="/search/cs?searchtype=author&query=Shobayo%2C+O">Olamilekan Shobayo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.13713v1-abstract-short" style="display: inline;"> The World Health Organisation (WHO) revealed approximately 280 million people in the world suffer from depression. Yet, existing studies on early-stage depression detection using machine learning (ML) techniques are limited. Prior studies have applied a single stand-alone algorithm, which is unable to deal with data complexities, prone to overfitting, and limited in generalization. To this end, ou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13713v1-abstract-full').style.display = 'inline'; document.getElementById('2409.13713v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13713v1-abstract-full" style="display: none;"> The World Health Organisation (WHO) revealed approximately 280 million people in the world suffer from depression. Yet, existing studies on early-stage depression detection using machine learning (ML) techniques are limited. Prior studies have applied a single stand-alone algorithm, which is unable to deal with data complexities, prone to overfitting, and limited in generalization. To this end, our paper examined the performance of several ML algorithms for early-stage depression detection using two benchmark social media datasets (D1 and D2). More specifically, we incorporated sentiment indicators to improve our model performance. Our experimental results showed that sentence bidirectional encoder representations from transformers (SBERT) numerical vectors fitted into the stacking ensemble model achieved comparable F1 scores of 69% in the dataset (D1) and 76% in the dataset (D2). Our findings suggest that utilizing sentiment indicators as an additional feature for depression detection yields an improved model performance, and thus, we recommend the development of a depressive term corpus for future work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13713v1-abstract-full').style.display = 'none'; document.getElementById('2409.13713v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.13833">arXiv:2407.13833</a> <span> [<a href="https://arxiv.org/pdf/2407.13833">pdf</a>, <a href="https://arxiv.org/format/2407.13833">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"> Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Haider%2C+E">Emman Haider</a>, <a href="/search/cs?searchtype=author&query=Perez-Becker%2C+D">Daniel Perez-Becker</a>, <a href="/search/cs?searchtype=author&query=Portet%2C+T">Thomas Portet</a>, <a href="/search/cs?searchtype=author&query=Madan%2C+P">Piyush Madan</a>, <a href="/search/cs?searchtype=author&query=Garg%2C+A">Amit Garg</a>, <a href="/search/cs?searchtype=author&query=Ashfaq%2C+A">Atabak Ashfaq</a>, <a href="/search/cs?searchtype=author&query=Majercak%2C+D">David Majercak</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+W">Wen Wen</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+D">Dongwoo Kim</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Ziyi Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianwen Zhang</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Bullwinkel%2C+B">Blake Bullwinkel</a>, <a href="/search/cs?searchtype=author&query=Pouliot%2C+M">Martin Pouliot</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=Herrera%2C+S">Solianna Herrera</a>, <a href="/search/cs?searchtype=author&query=Warreth%2C+S">Shahed Warreth</a>, <a href="/search/cs?searchtype=author&query=Engler%2C+M">Maggie Engler</a>, <a href="/search/cs?searchtype=author&query=Lopez%2C+G">Gary Lopez</a>, <a href="/search/cs?searchtype=author&query=Chikanov%2C+N">Nina Chikanov</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=Lutz%2C+R">Roman Lutz</a>, <a href="/search/cs?searchtype=author&query=Lundeen%2C+R">Richard Lundeen</a> , et al. (6 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="2407.13833v2-abstract-short" style="display: inline;"> Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13833v2-abstract-full').style.display = 'inline'; document.getElementById('2407.13833v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.13833v2-abstract-full" style="display: none;"> Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks. Finally, we include additional red teaming strategies and evaluations that were used to test the safety behavior of Phi-3.5-mini and Phi-3.5-MoE, which were optimized for multilingual capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13833v2-abstract-full').style.display = 'none'; document.getElementById('2407.13833v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08840">arXiv:2407.08840</a> <span> [<a href="https://arxiv.org/pdf/2407.08840">pdf</a>, <a href="https://arxiv.org/format/2407.08840">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> Data-driven Model Reduction for Soft Robots via Lagrangian Operator Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Adibnazari%2C+I">Iman Adibnazari</a>, <a href="/search/cs?searchtype=author&query=Cervera-Torralba%2C+J">Jacobo Cervera-Torralba</a>, <a href="/search/cs?searchtype=author&query=Tolley%2C+M+T">Michael T. Tolley</a>, <a href="/search/cs?searchtype=author&query=Kramer%2C+B">Boris Kramer</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.08840v1-abstract-short" style="display: inline;"> Data-driven model reduction methods provide a nonintrusive way of constructing computationally efficient surrogates of high-fidelity models for real-time control of soft robots. This work leverages the Lagrangian nature of the model equations to derive structure-preserving linear reduced-order models via Lagrangian Operator Inference and compares their performance with prominent linear model reduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08840v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08840v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08840v1-abstract-full" style="display: none;"> Data-driven model reduction methods provide a nonintrusive way of constructing computationally efficient surrogates of high-fidelity models for real-time control of soft robots. This work leverages the Lagrangian nature of the model equations to derive structure-preserving linear reduced-order models via Lagrangian Operator Inference and compares their performance with prominent linear model reduction techniques through an anguilliform swimming soft robot model example with 231,336 degrees of freedom. The case studies demonstrate that preserving the underlying Lagrangian structure leads to learned models with higher predictive accuracy and robustness to unseen inputs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08840v1-abstract-full').style.display = 'none'; document.getElementById('2407.08840v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.02119">arXiv:2407.02119</a> <span> [<a href="https://arxiv.org/pdf/2407.02119">pdf</a>, <a href="https://arxiv.org/format/2407.02119">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yifang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuohang Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Ziyi Yang</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Karampatziakis%2C+N">Nikos Karampatziakis</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Donghan Yu</a>, <a href="/search/cs?searchtype=author&query=Jamieson%2C+K">Kevin Jamieson</a>, <a href="/search/cs?searchtype=author&query=Du%2C+S+S">Simon Shaolei Du</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yelong Shen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.02119v2-abstract-short" style="display: inline;"> Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}. While traditional methods rely on offline preference dataset constructions, recent approaches have shifted towards online settings, where a learner uses a small amount of labeled seed data and a large pool of unlab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02119v2-abstract-full').style.display = 'inline'; document.getElementById('2407.02119v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.02119v2-abstract-full" style="display: none;"> Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}. While traditional methods rely on offline preference dataset constructions, recent approaches have shifted towards online settings, where a learner uses a small amount of labeled seed data and a large pool of unlabeled prompts to iteratively construct new preference data through self-generated responses and high-quality reward/preference feedback. However, most current online algorithms still focus on preference labeling during policy model updating with given feedback oracles, which incurs significant expert query costs. \textit{We are the first to explore cost-effective proxy reward oracles construction strategies for further labeling preferences or rewards with extremely limited labeled data and expert query budgets}. Our approach introduces two key innovations: (1) on-policy query to avoid OOD and imbalance issues in seed data, and (2) active learning to select the most informative data for preference queries. Using these methods, we train a evaluation model with minimal expert-labeled data, which then effectively labels nine times more preference pairs for further RLHF training. For instance, our model using Direct Preference Optimization (DPO) gains around over 1% average improvement on AlpacaEval2, MMLU-5shot and MMLU-0shot, with only 1.7K query cost. Our methodology is orthogonal to other direct expert query-based strategies and therefore might be integrated with them to further reduce query costs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02119v2-abstract-full').style.display = 'none'; document.getElementById('2407.02119v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.13831">arXiv:2406.13831</a> <span> [<a href="https://arxiv.org/pdf/2406.13831">pdf</a>, <a href="https://arxiv.org/format/2406.13831">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"> A Comprehensive Overview of GPU Accelerated Databases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshit Sharma</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Anmol Sharma</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.13831v1-abstract-short" style="display: inline;"> Over the past decade, the landscape of data analytics has seen a notable shift towards heterogeneous architectures, particularly the integration of GPUs to enhance overall performance. In the realm of in-memory analytics, which often grapples with memory bandwidth constraints, the adoption of GPUs has proven advantageous, thanks to their superior bandwidth capabilities. The parallel processing pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13831v1-abstract-full').style.display = 'inline'; document.getElementById('2406.13831v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13831v1-abstract-full" style="display: none;"> Over the past decade, the landscape of data analytics has seen a notable shift towards heterogeneous architectures, particularly the integration of GPUs to enhance overall performance. In the realm of in-memory analytics, which often grapples with memory bandwidth constraints, the adoption of GPUs has proven advantageous, thanks to their superior bandwidth capabilities. The parallel processing prowess of GPUs stands out, providing exceptional efficiency for data-intensive workloads and outpacing traditional CPUs in terms of data processing speed. While GPU databases capitalize on these strengths, there remains a scarcity of comparative studies across different GPU systems. In light of this emerging interest in GPU databases for data analytics, this paper proposes a survey encompassing multiple GPU database systems. The focus will be on elucidating the underlying mechanisms employed to deliver results and key performance metrics, utilizing benchmarks such as SSB and TPCH. This undertaking aims to shed light on new avenues for research within the realm of GPU databases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13831v1-abstract-full').style.display = 'none'; document.getElementById('2406.13831v1-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> 19 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10362">arXiv:2406.10362</a> <span> [<a href="https://arxiv.org/pdf/2406.10362">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> A Comparison of the Performance of the Molecular Dynamics Simulation Package GROMACS Implemented in the SYCL and CUDA Programming Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Apanasevich%2C+L">L. Apanasevich</a>, <a href="/search/cs?searchtype=author&query=Kale%2C+Y">Yogesh Kale</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Sokovic%2C+A+M">Ana Marija Sokovic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10362v1-abstract-short" style="display: inline;"> For many years, systems running Nvidia-based GPU architectures have dominated the heterogeneous supercomputer landscape. However, recently GPU chipsets manufactured by Intel and AMD have cut into this market and can now be found in some of the worlds fastest supercomputers. The June 2023 edition of the TOP500 list of supercomputers ranks the Frontier supercomputer at the Oak Ridge National Laborat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10362v1-abstract-full').style.display = 'inline'; document.getElementById('2406.10362v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10362v1-abstract-full" style="display: none;"> For many years, systems running Nvidia-based GPU architectures have dominated the heterogeneous supercomputer landscape. However, recently GPU chipsets manufactured by Intel and AMD have cut into this market and can now be found in some of the worlds fastest supercomputers. The June 2023 edition of the TOP500 list of supercomputers ranks the Frontier supercomputer at the Oak Ridge National Laboratory in Tennessee as the top system in the world. This system features AMD Instinct 250 X GPUs and is currently the only true exascale computer in the world.The first framework that enabled support for heterogeneous platforms across multiple hardware vendors was OpenCL, in 2009. Since then a number of frameworks have been developed to support vendor agnostic heterogeneous environments including OpenMP, OpenCL, Kokkos, and SYCL. SYCL, which combines the concepts of OpenCL with the flexibility of single-source C++, is one of the more promising programming models for heterogeneous computing devices. One key advantage of this framework is that it provides a higher-level programming interface that abstracts away many of the hardware details than the other frameworks. This makes SYCL easier to learn and to maintain across multiple architectures and vendors. In n recent years, there has been growing interest in using heterogeneous computing architectures to accelerate molecular dynamics simulations. Some of the more popular molecular dynamics simulations include Amber, NAMD, and Gromacs. However, to the best of our knowledge, only Gromacs has been successfully ported to SYCL to date. In this paper, we compare the performance of GROMACS compiled using the SYCL and CUDA frameworks for a variety of standard GROMACS benchmarks. In addition, we compare its performance across three different Nvidia GPU chipsets, P100, V100, and A100. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10362v1-abstract-full').style.display = 'none'; document.getElementById('2406.10362v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.09520">arXiv:2406.09520</a> <span> [<a href="https://arxiv.org/pdf/2406.09520">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div 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/10.3390/educsci14060636">10.3390/educsci14060636 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Systematic Review of Generative AI for Teaching and Learning Practice </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ogunleye%2C+B">Bayode Ogunleye</a>, <a href="/search/cs?searchtype=author&query=Zakariyyah%2C+K+I">Kudirat Ibilola Zakariyyah</a>, <a href="/search/cs?searchtype=author&query=Ajao%2C+O">Oluwaseun Ajao</a>, <a href="/search/cs?searchtype=author&query=Olayinka%2C+O">Olakunle Olayinka</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemlata Sharma</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.09520v1-abstract-short" style="display: inline;"> The use of generative artificial intelligence (GenAI) in academia is a subjective and hotly debated topic. Currently, there are no agreed guidelines towards the usage of GenAI systems in higher education (HE) and, thus, it is still unclear how to make effective use of the technology for teaching and learning practice. This paper provides an overview of the current state of research on GenAI for te… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09520v1-abstract-full').style.display = 'inline'; document.getElementById('2406.09520v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.09520v1-abstract-full" style="display: none;"> The use of generative artificial intelligence (GenAI) in academia is a subjective and hotly debated topic. Currently, there are no agreed guidelines towards the usage of GenAI systems in higher education (HE) and, thus, it is still unclear how to make effective use of the technology for teaching and learning practice. This paper provides an overview of the current state of research on GenAI for teaching and learning in HE. To this end, this study conducted a systematic review of relevant studies indexed by Scopus, using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The search criteria revealed a total of 625 research papers, of which 355 met the final inclusion criteria. The findings from the review showed the current state and the future trends in documents, citations, document sources/authors, keywords, and co-authorship. The research gaps identified suggest that while some authors have looked at understanding the detection of AI-generated text, it may be beneficial to understand how GenAI can be incorporated into supporting the educational curriculum for assessments, teaching, and learning delivery. Furthermore, there is a need for additional interdisciplinary, multidimensional studies in HE through collaboration. This will strengthen the awareness and understanding of students, tutors, and other stakeholders, which will be instrumental in formulating guidelines, frameworks, and policies for GenAI usage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09520v1-abstract-full').style.display = 'none'; document.getElementById('2406.09520v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 10 figures, article published in Education Sciences</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.3 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Educ. Sci. 2024, 14, pp636 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.04449">arXiv:2406.04449</a> <span> [<a href="https://arxiv.org/pdf/2406.04449">pdf</a>, <a href="https://arxiv.org/format/2406.04449">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> MAIRA-2: Grounded Radiology Report Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Thieme%2C+A">Anja Thieme</a>, <a href="/search/cs?searchtype=author&query=Bond-Taylor%2C+S">Sam Bond-Taylor</a>, <a href="/search/cs?searchtype=author&query=Ilse%2C+M">Maximilian Ilse</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Salvatelli%2C+V">Valentina Salvatelli</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Meissen%2C+F">Felix Meissen</a>, <a href="/search/cs?searchtype=author&query=Ranjit%2C+M">Mercy Ranjit</a>, <a href="/search/cs?searchtype=author&query=Srivastav%2C+S">Shaury Srivastav</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+J">Julia Gong</a>, <a href="/search/cs?searchtype=author&query=Codella%2C+N+C+F">Noel C. F. Codella</a>, <a href="/search/cs?searchtype=author&query=Falck%2C+F">Fabian Falck</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria Teodora Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S+L">Stephanie L. Hyland</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.04449v2-abstract-short" style="display: inline;"> Radiology reporting is a complex task requiring detailed medical image understanding and precise language generation, for which generative multimodal models offer a promising solution. However, to impact clinical practice, models must achieve a high level of both verifiable performance and utility. We augment the utility of automated report generation by incorporating localisation of individual fi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04449v2-abstract-full').style.display = 'inline'; document.getElementById('2406.04449v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.04449v2-abstract-full" style="display: none;"> Radiology reporting is a complex task requiring detailed medical image understanding and precise language generation, for which generative multimodal models offer a promising solution. However, to impact clinical practice, models must achieve a high level of both verifiable performance and utility. We augment the utility of automated report generation by incorporating localisation of individual findings on the image - a task we call grounded report generation - and enhance performance by incorporating realistic reporting context as inputs. We design a novel evaluation framework (RadFact) leveraging the logical inference capabilities of large language models (LLMs) to quantify report correctness and completeness at the level of individual sentences, while supporting the new task of grounded reporting. We develop MAIRA-2, a large radiology-specific multimodal model designed to generate chest X-ray reports with and without grounding. MAIRA-2 achieves state of the art on existing report generation benchmarks and establishes the novel task of grounded report generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04449v2-abstract-full').style.display = 'none'; document.getElementById('2406.04449v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">72 pages, 21 figures. v2 updates the model and adds results on the PadChest-GR dataset</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.19332">arXiv:2405.19332</a> <span> [<a href="https://arxiv.org/pdf/2405.19332">pdf</a>, <a href="https://arxiv.org/format/2405.19332">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Self-Exploring Language Models: Active Preference Elicitation for Online Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shenao Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Donghan Yu</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+H">Han Zhong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhihan Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Ziyi Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuohang Wang</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+H">Hany Hassan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhaoran Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.19332v3-abstract-short" style="display: inline;"> Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed dataset, online feedback collection from humans or AI on model generations typically leads to more capable reward models and better-aligned LLMs through an iter… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19332v3-abstract-full').style.display = 'inline'; document.getElementById('2405.19332v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.19332v3-abstract-full" style="display: none;"> Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed dataset, online feedback collection from humans or AI on model generations typically leads to more capable reward models and better-aligned LLMs through an iterative process. However, achieving a globally accurate reward model requires systematic exploration to generate diverse responses that span the vast space of natural language. Random sampling from standard reward-maximizing LLMs alone is insufficient to fulfill this requirement. To address this issue, we propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. By solving the inner-level problem with the reparameterized reward function, the resulting algorithm, named Self-Exploring Language Models (SELM), eliminates the need for a separate RM and iteratively updates the LLM with a straightforward objective. Compared to Direct Preference Optimization (DPO), the SELM objective reduces indiscriminate favor of unseen extrapolations and enhances exploration efficiency. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks such as MT-Bench and AlpacaEval 2.0, as well as various standard academic benchmarks in different settings. Our code and models are available at https://github.com/shenao-zhang/SELM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19332v3-abstract-full').style.display = 'none'; document.getElementById('2405.19332v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.05299">arXiv:2405.05299</a> <span> [<a href="https://arxiv.org/pdf/2405.05299">pdf</a>, <a href="https://arxiv.org/format/2405.05299">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Challenges for Responsible AI Design and Workflow Integration in Healthcare: A Case Study of Automatic Feeding Tube Qualification in Radiology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thieme%2C+A">Anja Thieme</a>, <a href="/search/cs?searchtype=author&query=Rajamohan%2C+A">Abhijith Rajamohan</a>, <a href="/search/cs?searchtype=author&query=Cooper%2C+B">Benjamin Cooper</a>, <a href="/search/cs?searchtype=author&query=Groombridge%2C+H">Heather Groombridge</a>, <a href="/search/cs?searchtype=author&query=Simister%2C+R">Robert Simister</a>, <a href="/search/cs?searchtype=author&query=Wong%2C+B">Barney Wong</a>, <a href="/search/cs?searchtype=author&query=Woznitza%2C+N">Nicholas Woznitza</a>, <a href="/search/cs?searchtype=author&query=Pinnock%2C+M+A">Mark Ames Pinnock</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria Teodora Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Morrison%2C+C">Cecily Morrison</a>, <a href="/search/cs?searchtype=author&query=Richardson%2C+H">Hannah Richardson</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S+L">Stephanie L. Hyland</a>, <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Ranjit%2C+M">Mercy Ranjit</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Nori%2C+A">Aditya Nori</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+S">Stephen Harris</a>, <a href="/search/cs?searchtype=author&query=Jacob%2C+J">Joseph Jacob</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.05299v1-abstract-short" style="display: inline;"> Nasogastric tubes (NGTs) are feeding tubes that are inserted through the nose into the stomach to deliver nutrition or medication. If not placed correctly, they can cause serious harm, even death to patients. Recent AI developments demonstrate the feasibility of robustly detecting NGT placement from Chest X-ray images to reduce risks of sub-optimally or critically placed NGTs being missed or delay… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05299v1-abstract-full').style.display = 'inline'; document.getElementById('2405.05299v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.05299v1-abstract-full" style="display: none;"> Nasogastric tubes (NGTs) are feeding tubes that are inserted through the nose into the stomach to deliver nutrition or medication. If not placed correctly, they can cause serious harm, even death to patients. Recent AI developments demonstrate the feasibility of robustly detecting NGT placement from Chest X-ray images to reduce risks of sub-optimally or critically placed NGTs being missed or delayed in their detection, but gaps remain in clinical practice integration. In this study, we present a human-centered approach to the problem and describe insights derived following contextual inquiry and in-depth interviews with 15 clinical stakeholders. The interviews helped understand challenges in existing workflows, and how best to align technical capabilities with user needs and expectations. We discovered the trade-offs and complexities that need consideration when choosing suitable workflow stages, target users, and design configurations for different AI proposals. We explored how to balance AI benefits and risks for healthcare staff and patients within broader organizational and medical-legal constraints. We also identified data issues related to edge cases and data biases that affect model training and evaluation; how data documentation practices influence data preparation and labelling; and how to measure relevant AI outcomes reliably in future evaluations. We discuss how our work informs design and development of AI applications that are clinically useful, ethical, and acceptable in real-world healthcare services. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05299v1-abstract-full').style.display = 'none'; document.getElementById('2405.05299v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.5.m; I.2.m </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.19725">arXiv:2404.19725</a> <span> [<a href="https://arxiv.org/pdf/2404.19725">pdf</a>, <a href="https://arxiv.org/format/2404.19725">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Fairness Without Demographics in Human-Centered Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roy%2C+S">Shaily Roy</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshit Sharma</a>, <a href="/search/cs?searchtype=author&query=Salekin%2C+A">Asif Salekin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.19725v3-abstract-short" style="display: inline;"> Federated learning (FL) enables collaborative model training while preserving data privacy, making it suitable for decentralized human-centered AI applications. However, a significant research gap remains in ensuring fairness in these systems. Current fairness strategies in FL require knowledge of bias-creating/sensitive attributes, clashing with FL's privacy principles. Moreover, in human-centere… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.19725v3-abstract-full').style.display = 'inline'; document.getElementById('2404.19725v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.19725v3-abstract-full" style="display: none;"> Federated learning (FL) enables collaborative model training while preserving data privacy, making it suitable for decentralized human-centered AI applications. However, a significant research gap remains in ensuring fairness in these systems. Current fairness strategies in FL require knowledge of bias-creating/sensitive attributes, clashing with FL's privacy principles. Moreover, in human-centered datasets, sensitive attributes may remain latent. To tackle these challenges, we present a novel bias mitigation approach inspired by "Fairness without Demographics" in machine learning. The presented approach achieves fairness without needing knowledge of sensitive attributes by minimizing the top eigenvalue of the Hessian matrix during training, ensuring equitable loss landscapes across FL participants. Notably, we introduce a novel FL aggregation scheme that promotes participating models based on error rates and loss landscape curvature attributes, fostering fairness across the FL system. This work represents the first approach to attaining "Fairness without Demographics" in human-centered FL. Through comprehensive evaluation, our approach demonstrates effectiveness in balancing fairness and efficacy across various real-world applications, FL setups, and scenarios involving single and multiple bias-inducing factors, representing a significant advancement in human-centered FL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.19725v3-abstract-full').style.display = 'none'; document.getElementById('2404.19725v3-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14219">arXiv:2404.14219</a> <span> [<a href="https://arxiv.org/pdf/2404.14219">pdf</a>, <a href="https://arxiv.org/format/2404.14219">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"> Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abdin%2C+M">Marah Abdin</a>, <a href="/search/cs?searchtype=author&query=Aneja%2C+J">Jyoti Aneja</a>, <a href="/search/cs?searchtype=author&query=Awadalla%2C+H">Hany Awadalla</a>, <a href="/search/cs?searchtype=author&query=Awadallah%2C+A">Ahmed Awadallah</a>, <a href="/search/cs?searchtype=author&query=Awan%2C+A+A">Ammar Ahmad Awan</a>, <a href="/search/cs?searchtype=author&query=Bach%2C+N">Nguyen Bach</a>, <a href="/search/cs?searchtype=author&query=Bahree%2C+A">Amit Bahree</a>, <a href="/search/cs?searchtype=author&query=Bakhtiari%2C+A">Arash Bakhtiari</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+J">Jianmin Bao</a>, <a href="/search/cs?searchtype=author&query=Behl%2C+H">Harkirat Behl</a>, <a href="/search/cs?searchtype=author&query=Benhaim%2C+A">Alon Benhaim</a>, <a href="/search/cs?searchtype=author&query=Bilenko%2C+M">Misha Bilenko</a>, <a href="/search/cs?searchtype=author&query=Bjorck%2C+J">Johan Bjorck</a>, <a href="/search/cs?searchtype=author&query=Bubeck%2C+S">S茅bastien Bubeck</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+M">Martin Cai</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Q">Qin Cai</a>, <a href="/search/cs?searchtype=author&query=Chaudhary%2C+V">Vishrav Chaudhary</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dong Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weizhu Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yen-Chun Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yi-Ling Chen</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+H">Hao Cheng</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+P">Parul Chopra</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+X">Xiyang Dai</a> , et al. (104 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="2404.14219v4-abstract-short" style="display: inline;"> We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38 on MT-bench), despite being small enough to be deployed on a phone. Our training dataset is a scaled-up version… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14219v4-abstract-full').style.display = 'inline'; document.getElementById('2404.14219v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14219v4-abstract-full" style="display: none;"> We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38 on MT-bench), despite being small enough to be deployed on a phone. Our training dataset is a scaled-up version of the one used for phi-2, composed of heavily filtered publicly available web data and synthetic data. The model is also further aligned for robustness, safety, and chat format. We also provide parameter-scaling results with a 7B, 14B models trained for 4.8T tokens, called phi-3-small, phi-3-medium, both significantly more capable than phi-3-mini (e.g., respectively 75%, 78% on MMLU, and 8.7, 8.9 on MT-bench). To enhance multilingual, multimodal, and long-context capabilities, we introduce three models in the phi-3.5 series: phi-3.5-mini, phi-3.5-MoE, and phi-3.5-Vision. The phi-3.5-MoE, a 16 x 3.8B MoE model with 6.6 billion active parameters, achieves superior performance in language reasoning, math, and code tasks compared to other open-source models of similar scale, such as Llama 3.1 and the Mixtral series, and on par with Gemini-1.5-Flash and GPT-4o-mini. Meanwhile, phi-3.5-Vision, a 4.2 billion parameter model derived from phi-3.5-mini, excels in reasoning tasks and is adept at handling both single-image and text prompts, as well as multi-image and text prompts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14219v4-abstract-full').style.display = 'none'; document.getElementById('2404.14219v4-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">24 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/2404.05040">arXiv:2404.05040</a> <span> [<a href="https://arxiv.org/pdf/2404.05040">pdf</a>, <a href="https://arxiv.org/format/2404.05040">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="Dynamical Systems">math.DS</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.cma.2024.116865">10.1016/j.cma.2024.116865 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Lagrangian operator inference enhanced with structure-preserving machine learning for nonintrusive model reduction of mechanical systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Najera-Flores%2C+D+A">David A. Najera-Flores</a>, <a href="/search/cs?searchtype=author&query=Todd%2C+M+D">Michael D. Todd</a>, <a href="/search/cs?searchtype=author&query=Kramer%2C+B">Boris Kramer</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.05040v1-abstract-short" style="display: inline;"> Complex mechanical systems often exhibit strongly nonlinear behavior due to the presence of nonlinearities in the energy dissipation mechanisms, material constitutive relationships, or geometric/connectivity mechanics. Numerical modeling of these systems leads to nonlinear full-order models that possess an underlying Lagrangian structure. This work proposes a Lagrangian operator inference method e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05040v1-abstract-full').style.display = 'inline'; document.getElementById('2404.05040v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05040v1-abstract-full" style="display: none;"> Complex mechanical systems often exhibit strongly nonlinear behavior due to the presence of nonlinearities in the energy dissipation mechanisms, material constitutive relationships, or geometric/connectivity mechanics. Numerical modeling of these systems leads to nonlinear full-order models that possess an underlying Lagrangian structure. This work proposes a Lagrangian operator inference method enhanced with structure-preserving machine learning to learn nonlinear reduced-order models (ROMs) of nonlinear mechanical systems. This two-step approach first learns the best-fit linear Lagrangian ROM via Lagrangian operator inference and then presents a structure-preserving machine learning method to learn nonlinearities in the reduced space. The proposed approach can learn a structure-preserving nonlinear ROM purely from data, unlike the existing operator inference approaches that require knowledge about the mathematical form of nonlinear terms. From a machine learning perspective, it accelerates the training of the structure-preserving neural network by providing an informed prior, and it reduces the computational cost of the network training by operating on the reduced space. The method is first demonstrated on two simulated examples: a conservative nonlinear rod model and a two-dimensional nonlinear membrane with nonlinear internal damping. Finally, the method is demonstrated on an experimental dataset consisting of digital image correlation measurements taken from a lap-joint beam structure from which a predictive model is learned that captures amplitude-dependent frequency and damping characteristics accurately. The numerical results demonstrate that the proposed approach yields generalizable nonlinear ROMs that exhibit bounded energy error, capture the nonlinear characteristics reliably, and provide accurate long-time predictions outside the training data regime. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05040v1-abstract-full').style.display = 'none'; document.getElementById('2404.05040v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01036">arXiv:2404.01036</a> <span> [<a href="https://arxiv.org/pdf/2404.01036">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div 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/10.37074/jalt.2024.7.1.28">10.37074/jalt.2024.7.1.28 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Higher education assessment practice in the era of generative AI tools </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ogunleye%2C+B">Bayode Ogunleye</a>, <a href="/search/cs?searchtype=author&query=Zakariyyah%2C+K+I">Kudirat Ibilola Zakariyyah</a>, <a href="/search/cs?searchtype=author&query=Ajao%2C+O">Oluwaseun Ajao</a>, <a href="/search/cs?searchtype=author&query=Olayinka%2C+O">Olakunle Olayinka</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemlata Sharma</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.01036v1-abstract-short" style="display: inline;"> The higher education (HE) sector benefits every nation's economy and society at large. However, their contributions are challenged by advanced technologies like generative artificial intelligence (GenAI) tools. In this paper, we provide a comprehensive assessment of GenAI tools towards assessment and pedagogic practice and, subsequently, discuss the potential impacts. This study experimented using… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01036v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01036v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01036v1-abstract-full" style="display: none;"> The higher education (HE) sector benefits every nation's economy and society at large. However, their contributions are challenged by advanced technologies like generative artificial intelligence (GenAI) tools. In this paper, we provide a comprehensive assessment of GenAI tools towards assessment and pedagogic practice and, subsequently, discuss the potential impacts. This study experimented using three assessment instruments from data science, data analytics, and construction management disciplines. Our findings are two-fold: first, the findings revealed that GenAI tools exhibit subject knowledge, problem-solving, analytical, critical thinking, and presentation skills and thus can limit learning when used unethically. Secondly, the design of the assessment of certain disciplines revealed the limitations of the GenAI tools. Based on our findings, we made recommendations on how AI tools can be utilised for teaching and learning in HE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01036v1-abstract-full').style.display = 'none'; document.getElementById('2404.01036v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 7 tables published in the Journal of Applied Learning & Teaching</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7; I.2.10; H.3.3 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Higher education assessment practice in the era of generative AI tools. (2024). Journal of applied learning and teaching, 7(1) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.19073">arXiv:2403.19073</a> <span> [<a href="https://arxiv.org/pdf/2403.19073">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Dataflow-Aware PIM-Enabled Manycore Architecture for Deep Learning Workloads </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Narang%2C+G">Gaurav Narang</a>, <a href="/search/cs?searchtype=author&query=Doppa%2C+J+R">Janardhan Rao Doppa</a>, <a href="/search/cs?searchtype=author&query=Ogras%2C+U">Umit Ogras</a>, <a href="/search/cs?searchtype=author&query=Pande%2C+P+P">Partha Pratim Pande</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.19073v1-abstract-short" style="display: inline;"> Processing-in-memory (PIM) has emerged as an enabler for the energy-efficient and high-performance acceleration of deep learning (DL) workloads. Resistive random-access memory (ReRAM) is one of the most promising technologies to implement PIM. However, as the complexity of Deep convolutional neural networks (DNNs) grows, we need to design a manycore architecture with multiple ReRAM-based processin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.19073v1-abstract-full').style.display = 'inline'; document.getElementById('2403.19073v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.19073v1-abstract-full" style="display: none;"> Processing-in-memory (PIM) has emerged as an enabler for the energy-efficient and high-performance acceleration of deep learning (DL) workloads. Resistive random-access memory (ReRAM) is one of the most promising technologies to implement PIM. However, as the complexity of Deep convolutional neural networks (DNNs) grows, we need to design a manycore architecture with multiple ReRAM-based processing elements (PEs) on a single chip. Existing PIM-based architectures mostly focus on computation while ignoring the role of communication. ReRAM-based tiled manycore architectures often involve many Processing Elements (PEs), which need to be interconnected via an efficient on-chip communication infrastructure. Simply allocating more resources (ReRAMs) to speed up only computation is ineffective if the communication infrastructure cannot keep up with it. In this paper, we highlight the design principles of a dataflow-aware PIM-enabled manycore platform tailor-made for various types of DL workloads. We consider the design challenges with both 2.5D interposer- and 3D integration-enabled architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.19073v1-abstract-full').style.display = 'none'; document.getElementById('2403.19073v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Presented at DATE Conference, Valencia, Spain 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/2403.17306">arXiv:2403.17306</a> <span> [<a href="https://arxiv.org/pdf/2403.17306">pdf</a>, <a href="https://arxiv.org/format/2403.17306">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"> Visual Hallucination: Definition, Quantification, and Prescriptive Remediations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rani%2C+A">Anku Rani</a>, <a href="/search/cs?searchtype=author&query=Rawte%2C+V">Vipula Rawte</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshad Sharma</a>, <a href="/search/cs?searchtype=author&query=Anand%2C+N">Neeraj Anand</a>, <a href="/search/cs?searchtype=author&query=Rajbangshi%2C+K">Krishnav Rajbangshi</a>, <a href="/search/cs?searchtype=author&query=Sheth%2C+A">Amit Sheth</a>, <a href="/search/cs?searchtype=author&query=Das%2C+A">Amitava 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="2403.17306v2-abstract-short" style="display: inline;"> The troubling rise of hallucination presents perhaps the most significant impediment to the advancement of responsible AI. In recent times, considerable research has focused on detecting and mitigating hallucination in Large Language Models (LLMs). However, it's worth noting that hallucination is also quite prevalent in Vision-Language models (VLMs). In this paper, we offer a fine-grained discours… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17306v2-abstract-full').style.display = 'inline'; document.getElementById('2403.17306v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17306v2-abstract-full" style="display: none;"> The troubling rise of hallucination presents perhaps the most significant impediment to the advancement of responsible AI. In recent times, considerable research has focused on detecting and mitigating hallucination in Large Language Models (LLMs). However, it's worth noting that hallucination is also quite prevalent in Vision-Language models (VLMs). In this paper, we offer a fine-grained discourse on profiling VLM hallucination based on two tasks: i) image captioning, and ii) Visual Question Answering (VQA). We delineate eight fine-grained orientations of visual hallucination: i) Contextual Guessing, ii) Identity Incongruity, iii) Geographical Erratum, iv) Visual Illusion, v) Gender Anomaly, vi) VLM as Classifier, vii) Wrong Reading, and viii) Numeric Discrepancy. We curate Visual HallucInation eLiciTation (VHILT), a publicly available dataset comprising 2,000 samples generated using eight VLMs across two tasks of captioning and VQA along with human annotations for the categories as mentioned earlier. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17306v2-abstract-full').style.display = 'none'; document.getElementById('2403.17306v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.14353">arXiv:2403.14353</a> <span> [<a href="https://arxiv.org/pdf/2403.14353">pdf</a>, <a href="https://arxiv.org/format/2403.14353">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</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/ISCA59077.2024.00093">10.1109/ISCA59077.2024.00093 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+Y">Yoonsung Kim</a>, <a href="/search/cs?searchtype=author&query=Oh%2C+C">Changhun Oh</a>, <a href="/search/cs?searchtype=author&query=Hwang%2C+J">Jinwoo Hwang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+W">Wonung Kim</a>, <a href="/search/cs?searchtype=author&query=Oh%2C+S">Seongryong Oh</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+Y">Yubin Lee</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hardik Sharma</a>, <a href="/search/cs?searchtype=author&query=Yazdanbakhsh%2C+A">Amir Yazdanbakhsh</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jongse Park</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.14353v3-abstract-short" style="display: inline;"> Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world deployment faces challenges due to their limited computational resources and battery power. To tackle these challenges, continuous learning exploits a lightweight "student" model at deployment (inference), leverages a l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14353v3-abstract-full').style.display = 'inline'; document.getElementById('2403.14353v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14353v3-abstract-full" style="display: none;"> Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world deployment faces challenges due to their limited computational resources and battery power. To tackle these challenges, continuous learning exploits a lightweight "student" model at deployment (inference), leverages a larger "teacher" model for labeling sampled data (labeling), and continuously retrains the student model to adapt to changing scenarios (retraining). This paper highlights the limitations in state-of-the-art continuous learning systems: (1) they focus on computations for retraining, while overlooking the compute needs for inference and labeling, (2) they rely on power-hungry GPUs, unsuitable for battery-operated autonomous systems, and (3) they are located on a remote centralized server, intended for multi-tenant scenarios, again unsuitable for autonomous systems due to privacy, network availability, and latency concerns. We propose a hardware-algorithm co-designed solution for continuous learning, DaCapo, that enables autonomous systems to perform concurrent executions of inference, labeling, and training in a performant and energy-efficient manner. DaCapo comprises (1) a spatially-partitionable and precision-flexible accelerator enabling parallel execution of kernels on sub-accelerators at their respective precisions, and (2) a spatiotemporal resource allocation algorithm that strategically navigates the resource-accuracy tradeoff space, facilitating optimal decisions for resource allocation to achieve maximal accuracy. Our evaluation shows that DaCapo achieves 6.5% and 5.5% higher accuracy than a state-of-the-art GPU-based continuous learning systems, Ekya and EOMU, respectively, while consuming 254x less power. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14353v3-abstract-full').style.display = 'none'; document.getElementById('2403.14353v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ISCA 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.12938">arXiv:2403.12938</a> <span> [<a href="https://arxiv.org/pdf/2403.12938">pdf</a>, <a href="https://arxiv.org/format/2403.12938">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"> Neural Differential Algebraic Equations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Koch%2C+J">James Koch</a>, <a href="/search/cs?searchtype=author&query=Shapiro%2C+M">Madelyn Shapiro</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Vrabie%2C+D">Draguna Vrabie</a>, <a href="/search/cs?searchtype=author&query=Drgona%2C+J">Jan Drgona</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.12938v1-abstract-short" style="display: inline;"> Differential-Algebraic Equations (DAEs) describe the temporal evolution of systems that obey both differential and algebraic constraints. Of particular interest are systems that contain implicit relationships between their components, such as conservation relationships. Here, we present Neural Differential-Algebraic Equations (NDAEs) suitable for data-driven modeling of DAEs. This methodology is b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12938v1-abstract-full').style.display = 'inline'; document.getElementById('2403.12938v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.12938v1-abstract-full" style="display: none;"> Differential-Algebraic Equations (DAEs) describe the temporal evolution of systems that obey both differential and algebraic constraints. Of particular interest are systems that contain implicit relationships between their components, such as conservation relationships. Here, we present Neural Differential-Algebraic Equations (NDAEs) suitable for data-driven modeling of DAEs. This methodology is built upon the concept of the Universal Differential Equation; that is, a model constructed as a system of Neural Ordinary Differential Equations informed by theory from particular science domains. In this work, we show that the proposed NDAEs abstraction is suitable for relevant system-theoretic data-driven modeling tasks. Presented examples include (i) the inverse problem of tank-manifold dynamics and (ii) discrepancy modeling of a network of pumps, tanks, and pipes. Our experiments demonstrate the proposed method's robustness to noise and extrapolation ability to (i) learn the behaviors of the system components and their interaction physics and (ii) disambiguate between data trends and mechanistic relationships contained in the system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12938v1-abstract-full').style.display = 'none'; document.getElementById('2403.12938v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.15115">arXiv:2402.15115</a> <span> [<a href="https://arxiv.org/pdf/2402.15115">pdf</a>, <a href="https://arxiv.org/format/2402.15115">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> </div> </div> <p class="title is-5 mathjax"> Physics-constrained polynomial chaos expansion for scientific machine learning and uncertainty quantification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Nov%C3%A1k%2C+L">Luk谩拧 Nov谩k</a>, <a href="/search/cs?searchtype=author&query=Shields%2C+M+D">Michael D. Shields</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.15115v2-abstract-short" style="display: inline;"> We present a novel physics-constrained polynomial chaos expansion as a surrogate modeling method capable of performing both scientific machine learning (SciML) and uncertainty quantification (UQ) tasks. The proposed method possesses a unique capability: it seamlessly integrates SciML into UQ and vice versa, which allows it to quantify the uncertainties in SciML tasks effectively and leverage SciML… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15115v2-abstract-full').style.display = 'inline'; document.getElementById('2402.15115v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.15115v2-abstract-full" style="display: none;"> We present a novel physics-constrained polynomial chaos expansion as a surrogate modeling method capable of performing both scientific machine learning (SciML) and uncertainty quantification (UQ) tasks. The proposed method possesses a unique capability: it seamlessly integrates SciML into UQ and vice versa, which allows it to quantify the uncertainties in SciML tasks effectively and leverage SciML for improved uncertainty assessment during UQ-related tasks. The proposed surrogate model can effectively incorporate a variety of physical constraints, such as governing partial differential equations (PDEs) with associated initial and boundary conditions constraints, inequality-type constraints (e.g., monotonicity, convexity, non-negativity, among others), and additional a priori information in the training process to supplement limited data. This ensures physically realistic predictions and significantly reduces the need for expensive computational model evaluations to train the surrogate model. Furthermore, the proposed method has a built-in uncertainty quantification (UQ) feature to efficiently estimate output uncertainties. To demonstrate the effectiveness of the proposed method, we apply it to a diverse set of problems, including linear/non-linear PDEs with deterministic and stochastic parameters, data-driven surrogate modeling of a complex physical system, and UQ of a stochastic system with parameters modeled as random fields. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15115v2-abstract-full').style.display = 'none'; document.getElementById('2402.15115v2-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">34 pages, 15 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/2402.14252">arXiv:2402.14252</a> <span> [<a href="https://arxiv.org/pdf/2402.14252">pdf</a>, <a href="https://arxiv.org/format/2402.14252">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/10.1145/3613904.3642013">10.1145/3613904.3642013 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yildirim%2C+N">Nur Yildirim</a>, <a href="/search/cs?searchtype=author&query=Richardson%2C+H">Hannah Richardson</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria T. Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Bajwa%2C+J">Junaid Bajwa</a>, <a href="/search/cs?searchtype=author&query=Jacob%2C+J">Joseph Jacob</a>, <a href="/search/cs?searchtype=author&query=Pinnock%2C+M+A">Mark A. Pinnock</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+S">Stephen Harris</a>, <a href="/search/cs?searchtype=author&query=de+Castro%2C+D+C">Daniel Coelho de Castro</a>, <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S+L">Stephanie L. Hyland</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+P">Pratik Ghosh</a>, <a href="/search/cs?searchtype=author&query=Ranjit%2C+M">Mercy Ranjit</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M">Matthew Lungren</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Nori%2C+A">Aditya Nori</a>, <a href="/search/cs?searchtype=author&query=Thieme%2C+A">Anja Thieme</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.14252v1-abstract-short" style="display: inline;"> Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology, vision-language models (VLMs) achieve good performance results for tasks such as generating radiology findings based on a patient's medical image, or answering visual que… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14252v1-abstract-full').style.display = 'inline'; document.getElementById('2402.14252v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.14252v1-abstract-full" style="display: none;"> Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology, vision-language models (VLMs) achieve good performance results for tasks such as generating radiology findings based on a patient's medical image, or answering visual questions (e.g., 'Where are the nodules in this chest X-ray?'). However, the clinical utility of potential applications of these capabilities is currently underexplored. We engaged in an iterative, multidisciplinary design process to envision clinically relevant VLM interactions, and co-designed four VLM use concepts: Draft Report Generation, Augmented Report Review, Visual Search and Querying, and Patient Imaging History Highlights. We studied these concepts with 13 radiologists and clinicians who assessed the VLM concepts as valuable, yet articulated many design considerations. Reflecting on our findings, we discuss implications for integrating VLM capabilities in radiology, and for healthcare AI more generally. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14252v1-abstract-full').style.display = 'none'; document.getElementById('2402.14252v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">to appear at CHI 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/2402.04082">arXiv:2402.04082</a> <span> [<a href="https://arxiv.org/pdf/2402.04082">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="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</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/10.3390/analytics3010003">10.3390/analytics3010003 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Optimal House Price Prediction Algorithm: XGBoost </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemlata Sharma</a>, <a href="/search/cs?searchtype=author&query=Harsora%2C+H">Hitesh Harsora</a>, <a href="/search/cs?searchtype=author&query=Ogunleye%2C+B">Bayode Ogunleye</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.04082v1-abstract-short" style="display: inline;"> An accurate prediction of house prices is a fundamental requirement for various sectors including real estate and mortgage lending. It is widely recognized that a property value is not solely determined by its physical attributes but is significantly influenced by its surrounding neighbourhood. Meeting the diverse housing needs of individuals while balancing budget constraints is a primary concern… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04082v1-abstract-full').style.display = 'inline'; document.getElementById('2402.04082v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.04082v1-abstract-full" style="display: none;"> An accurate prediction of house prices is a fundamental requirement for various sectors including real estate and mortgage lending. It is widely recognized that a property value is not solely determined by its physical attributes but is significantly influenced by its surrounding neighbourhood. Meeting the diverse housing needs of individuals while balancing budget constraints is a primary concern for real estate developers. To this end, we addressed the house price prediction problem as a regression task and thus employed various machine learning techniques capable of expressing the significance of independent variables. We made use of the housing dataset of Ames City in Iowa, USA to compare support vector regressor, random forest regressor, XGBoost, multilayer perceptron and multiple linear regression algorithms for house price prediction. Afterwards, we identified the key factors that influence housing costs. Our results show that XGBoost is the best performing model for house price prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04082v1-abstract-full').style.display = 'none'; document.getElementById('2402.04082v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, Journal of Analytics</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.3 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Analytics, 3(1), 30-45 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.14943">arXiv:2401.14943</a> <span> [<a href="https://arxiv.org/pdf/2401.14943">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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/10.3390/analytics3010005">10.3390/analytics3010005 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Analysing the Influence of Macroeconomic Factors on Credit Risk in the UK Banking Sector </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemlata Sharma</a>, <a href="/search/cs?searchtype=author&query=Andhalkar%2C+A">Aparna Andhalkar</a>, <a href="/search/cs?searchtype=author&query=Ajao%2C+O">Oluwaseun Ajao</a>, <a href="/search/cs?searchtype=author&query=Ogunleye%2C+B">Bayode Ogunleye</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.14943v1-abstract-short" style="display: inline;"> Macroeconomic factors have a critical impact on banking credit risk, which cannot be directly controlled by banks, and therefore, there is a need for an early credit risk warning system based on the macroeconomy. By comparing different predictive models (traditional statistical and machine learning algorithms), this study aims to examine the macroeconomic determinants impact on the UK banking cred… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.14943v1-abstract-full').style.display = 'inline'; document.getElementById('2401.14943v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.14943v1-abstract-full" style="display: none;"> Macroeconomic factors have a critical impact on banking credit risk, which cannot be directly controlled by banks, and therefore, there is a need for an early credit risk warning system based on the macroeconomy. By comparing different predictive models (traditional statistical and machine learning algorithms), this study aims to examine the macroeconomic determinants impact on the UK banking credit risk and assess the most accurate credit risk estimate using predictive analytics. This study found that the variance-based multi-split decision tree algorithm is the most precise predictive model with interpretable, reliable, and robust results. Our model performance achieved 95% accuracy and evidenced that unemployment and inflation rate are significant credit risk predictors in the UK banking context. Our findings provided valuable insights such as a positive association between credit risk and inflation, the unemployment rate, and national savings, as well as a negative relationship between credit risk and national debt, total trade deficit, and national income. In addition, we empirically showed the relationship between national savings and non-performing loans, thus proving the paradox of thrift. These findings benefit the credit risk management team in monitoring the macroeconomic factors thresholds and implementing critical reforms to mitigate credit risk. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.14943v1-abstract-full').style.display = 'none'; document.getElementById('2401.14943v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages, 10 figures, published in Analytics 2024, Volume 3, Issue 1, 63-83</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.12476">arXiv:2401.12476</a> <span> [<a href="https://arxiv.org/pdf/2401.12476">pdf</a>, <a href="https://arxiv.org/format/2401.12476">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Dynamical Systems">math.DS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> </div> </div> <p class="title is-5 mathjax"> Bayesian identification of nonseparable Hamiltonians with multiplicative noise using deep learning and reduced-order modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Galioto%2C+N">Nicholas Galioto</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Kramer%2C+B">Boris Kramer</a>, <a href="/search/cs?searchtype=author&query=Gorodetsky%2C+A+A">Alex Arkady Gorodetsky</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.12476v3-abstract-short" style="display: inline;"> This paper presents a structure-preserving Bayesian approach for learning nonseparable Hamiltonian systems using stochastic dynamic models allowing for statistically-dependent, vector-valued additive and multiplicative measurement noise. The approach is comprised of three main facets. First, we derive a Gaussian filter for a statistically-dependent, vector-valued, additive and multiplicative noise… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.12476v3-abstract-full').style.display = 'inline'; document.getElementById('2401.12476v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.12476v3-abstract-full" style="display: none;"> This paper presents a structure-preserving Bayesian approach for learning nonseparable Hamiltonian systems using stochastic dynamic models allowing for statistically-dependent, vector-valued additive and multiplicative measurement noise. The approach is comprised of three main facets. First, we derive a Gaussian filter for a statistically-dependent, vector-valued, additive and multiplicative noise model that is needed to evaluate the likelihood within the Bayesian posterior. Second, we develop a novel algorithm for cost-effective application of Bayesian system identification to high-dimensional systems. Third, we demonstrate how structure-preserving methods can be incorporated into the proposed framework, using nonseparable Hamiltonians as an illustrative system class. We assess the method's performance based on the forecasting accuracy of a model estimated from single-trajectory data. We compare the Bayesian method to a state-of-the-art machine learning method on a canonical nonseparable Hamiltonian model and a chaotic double pendulum model with small, noisy training datasets. The results show that using the Bayesian posterior as a training objective can yield upwards of 724 times improvement in Hamiltonian mean squared error using training data with up to 10% multiplicative noise compared to a standard training objective. Lastly, we demonstrate the utility of the novel algorithm for parameter estimation of a 64-dimensional model of the spatially-discretized nonlinear Schr枚dinger equation with data corrupted by up to 20% multiplicative noise. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.12476v3-abstract-full').style.display = 'none'; document.getElementById('2401.12476v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.10815">arXiv:2401.10815</a> <span> [<a href="https://arxiv.org/pdf/2401.10815">pdf</a>, <a href="https://arxiv.org/format/2401.10815">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 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/10.1038/s42256-024-00965-w">10.1038/s42256-024-00965-w <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Exploring scalable medical image encoders beyond text supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Bond-Taylor%2C+S">Sam Bond-Taylor</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Salvatelli%2C+V">Valentina Salvatelli</a>, <a href="/search/cs?searchtype=author&query=Ilse%2C+M">Maximilian Ilse</a>, <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria Teodora Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Codella%2C+N">Noel Codella</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S+L">Stephanie L. Hyland</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.10815v3-abstract-short" style="display: inline;"> Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains. However, the computed features are limited by the information contained in the text, which is particularly problematic in medical imaging, where the findings d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.10815v3-abstract-full').style.display = 'inline'; document.getElementById('2401.10815v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.10815v3-abstract-full" style="display: none;"> Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains. However, the computed features are limited by the information contained in the text, which is particularly problematic in medical imaging, where the findings described by radiologists focus on specific observations. This challenge is compounded by the scarcity of paired imaging-text data due to concerns over leakage of personal health information. In this work, we fundamentally challenge the prevailing reliance on language supervision for learning general-purpose biomedical imaging encoders. We introduce RAD-DINO, a biomedical image encoder pre-trained solely on unimodal biomedical imaging data that obtains similar or greater performance than state-of-the-art biomedical language-supervised models on a diverse range of benchmarks. Specifically, the quality of learned representations is evaluated on standard imaging tasks (classification and semantic segmentation), and a vision-language alignment task (text report generation from images). To further demonstrate the drawback of language supervision, we show that features from RAD-DINO correlate with other medical records (e.g., sex or age) better than language-supervised models, which are generally not mentioned in radiology reports. Finally, we conduct a series of ablations determining the factors in RAD-DINO's performance; notably, we observe that RAD-DINO's downstream performance scales well with the quantity and diversity of training data, demonstrating that image-only supervision is a scalable approach for training a foundational biomedical image encoder. Model weights of RAD-DINO trained on publicly available datasets are available at https://huggingface.co/microsoft/rad-dino. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.10815v3-abstract-full').style.display = 'none'; document.getElementById('2401.10815v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Nature Machine Intelligence (2025) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.12865">arXiv:2312.12865</a> <span> [<a href="https://arxiv.org/pdf/2312.12865">pdf</a>, <a href="https://arxiv.org/format/2312.12865">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 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/10.1007/978-3-031-73254-6_21">10.1007/978-3-031-73254-6_21 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> RadEdit: stress-testing biomedical vision models via diffusion image editing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Bond-Taylor%2C+S">Sam Bond-Taylor</a>, <a href="/search/cs?searchtype=author&query=Sanchez%2C+P+P">Pedro P. Sanchez</a>, <a href="/search/cs?searchtype=author&query=van+Breugel%2C+B">Boris van Breugel</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Salvatelli%2C+V">Valentina Salvatelli</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T+A">Maria T. A. Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Richardson%2C+H">Hannah Richardson</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Nori%2C+A">Aditya Nori</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a>, <a href="/search/cs?searchtype=author&query=Ilse%2C+M">Maximilian Ilse</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.12865v3-abstract-short" style="display: inline;"> Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. This work proposes using generative image editing to simulate dataset shifts and diagnose failure modes of biomedical vision models; this can be used in advance of deployment to assess readiness, potentially reducing cost a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12865v3-abstract-full').style.display = 'inline'; document.getElementById('2312.12865v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.12865v3-abstract-full" style="display: none;"> Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. This work proposes using generative image editing to simulate dataset shifts and diagnose failure modes of biomedical vision models; this can be used in advance of deployment to assess readiness, potentially reducing cost and patient harm. Existing editing methods can produce undesirable changes, with spurious correlations learned due to the co-occurrence of disease and treatment interventions, limiting practical applicability. To address this, we train a text-to-image diffusion model on multiple chest X-ray datasets and introduce a new editing method RadEdit that uses multiple masks, if present, to constrain changes and ensure consistency in the edited images. We consider three types of dataset shifts: acquisition shift, manifestation shift, and population shift, and demonstrate that our approach can diagnose failures and quantify model robustness without additional data collection, complementing more qualitative tools for explainable AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12865v3-abstract-full').style.display = 'none'; document.getElementById('2312.12865v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> European Conference on Computer Vision (ECCV) 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.11750">arXiv:2312.11750</a> <span> [<a href="https://arxiv.org/pdf/2312.11750">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Heterogeneous Chiplet Architecture for Accelerating End-to-End Transformer Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Dhingra%2C+P">Pratyush Dhingra</a>, <a href="/search/cs?searchtype=author&query=Doppa%2C+J+R">Janardhan Rao Doppa</a>, <a href="/search/cs?searchtype=author&query=Ogras%2C+U">Umit Ogras</a>, <a href="/search/cs?searchtype=author&query=Pande%2C+P+P">Partha Pratim Pande</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.11750v2-abstract-short" style="display: inline;"> Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across various deep learning tasks. This trend of ever-increasing model size has given rise to new challenges in terms of memory and compute requirements. Conventional… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11750v2-abstract-full').style.display = 'inline'; document.getElementById('2312.11750v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.11750v2-abstract-full" style="display: none;"> Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across various deep learning tasks. This trend of ever-increasing model size has given rise to new challenges in terms of memory and compute requirements. Conventional computing platforms, including GPUs, suffer from suboptimal performance due to the memory demands imposed by models with millions/billions of parameters. The emerging chiplet-based platforms provide a new avenue for compute- and data-intensive machine learning (ML) applications enabled by a Network-on-Interposer (NoI). However, designing suitable hardware accelerators for executing Transformer inference workloads is challenging due to a wide variety of complex computing kernels in the Transformer architecture. In this paper, we leverage chiplet-based heterogeneous integration (HI) to design a high-performance and energy-efficient multi-chiplet platform to accelerate transformer workloads. We demonstrate that the proposed NoI architecture caters to the data access patterns inherent in a transformer model. The optimized placement of the chiplets and the associated NoI links and routers enable superior performance compared to the state-of-the-art hardware accelerators. The proposed NoI-based architecture demonstrates scalability across varying transformer models and improves latency and energy efficiency by up to 11.8x and 2.36x, respectively when compared with the existing state-of-the-art architecture HAIMA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11750v2-abstract-full').style.display = 'none'; document.getElementById('2312.11750v2-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">v1</span> submitted 18 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in ACM Transactions on Design Automation of Electronic Systems, 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/2312.11395">arXiv:2312.11395</a> <span> [<a href="https://arxiv.org/pdf/2312.11395">pdf</a>, <a href="https://arxiv.org/format/2312.11395">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"> Verb Categorisation for Hindi Word Problem Solving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+P">Pruthwik Mishra</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+D+M">Dipti Misra Sharma</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.11395v1-abstract-short" style="display: inline;"> Word problem Solving is a challenging NLP task that deals with solving mathematical problems described in natural language. Recently, there has been renewed interest in developing word problem solvers for Indian languages. As part of this paper, we have built a Hindi arithmetic word problem solver which makes use of verbs. Additionally, we have created verb categorization data for Hindi. Verbs are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11395v1-abstract-full').style.display = 'inline'; document.getElementById('2312.11395v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.11395v1-abstract-full" style="display: none;"> Word problem Solving is a challenging NLP task that deals with solving mathematical problems described in natural language. Recently, there has been renewed interest in developing word problem solvers for Indian languages. As part of this paper, we have built a Hindi arithmetic word problem solver which makes use of verbs. Additionally, we have created verb categorization data for Hindi. Verbs are very important for solving word problems with addition/subtraction operations as they help us identify the set of operations required to solve the word problems. We propose a rule-based solver that uses verb categorisation to identify operations in a word problem and generate answers for it. To perform verb categorisation, we explore several approaches and present a comparative study. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11395v1-abstract-full').style.display = 'none'; document.getElementById('2312.11395v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 17 figures, ICON 2023 Conference</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/2312.10884">arXiv:2312.10884</a> <span> [<a href="https://arxiv.org/pdf/2312.10884">pdf</a>, <a href="https://arxiv.org/format/2312.10884">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Contextual Reinforcement Learning for Offshore Wind Farm Bidding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cole%2C+D">David Cole</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wei Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.10884v1-abstract-short" style="display: inline;"> We propose a framework for applying reinforcement learning to contextual two-stage stochastic optimization and apply this framework to the problem of energy market bidding of an off-shore wind farm. Reinforcement learning could potentially be used to learn close to optimal solutions for first stage variables of a two-stage stochastic program under different contexts. Under the proposed framework,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10884v1-abstract-full').style.display = 'inline'; document.getElementById('2312.10884v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.10884v1-abstract-full" style="display: none;"> We propose a framework for applying reinforcement learning to contextual two-stage stochastic optimization and apply this framework to the problem of energy market bidding of an off-shore wind farm. Reinforcement learning could potentially be used to learn close to optimal solutions for first stage variables of a two-stage stochastic program under different contexts. Under the proposed framework, these solutions would be learned without having to solve the full two-stage stochastic program. We present initial results of training using the DDPG algorithm and present intended future steps to improve performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10884v1-abstract-full').style.display = 'none'; document.getElementById('2312.10884v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.07979">arXiv:2312.07979</a> <span> [<a href="https://arxiv.org/pdf/2312.07979">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <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"> SLJP: Semantic Extraction based Legal Judgment Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Madambakam%2C+P">Prameela Madambakam</a>, <a href="/search/cs?searchtype=author&query=Rajmohan%2C+S">Shathanaa Rajmohan</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himangshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+T+A+C+P">Tummepalli Anka Chandrahas Purushotham Gupta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.07979v1-abstract-short" style="display: inline;"> Legal Judgment Prediction (LJP) is a judicial assistance system that recommends the legal components such as applicable statues, prison term and penalty term by analyzing the given input case document. Indian legal system is in the need of technical assistance such as artificial intelligence to solve the crores of pending cases in various courts for years and its being increased day to day. Most o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.07979v1-abstract-full').style.display = 'inline'; document.getElementById('2312.07979v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.07979v1-abstract-full" style="display: none;"> Legal Judgment Prediction (LJP) is a judicial assistance system that recommends the legal components such as applicable statues, prison term and penalty term by analyzing the given input case document. Indian legal system is in the need of technical assistance such as artificial intelligence to solve the crores of pending cases in various courts for years and its being increased day to day. Most of the existing Indian models did not adequately concentrate on the semantics embedded in the fact description (FD) that impacts the decision. The proposed semantic extraction based LJP (SLJP) model provides the advantages of pretrained transformers for complex unstructured legal case document understanding and to generate embeddings. The model draws the in-depth semantics of the given FD at multiple levels i.e., chunk and case document level by following the divide and conquer approach. It creates the concise view of the given fact description using the extracted semantics as per the original court case document structure and predicts judgment using attention mechanism. We tested the model performance on two available Indian datasets Indian Legal Documents corpus (ILDC) and Indian Legal Statue Identification (ILSI) and got promising results. Also shown the highest performance and less performance degradation for increased epochs than base models on ILDC dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.07979v1-abstract-full').style.display = 'none'; document.getElementById('2312.07979v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.03989">arXiv:2312.03989</a> <span> [<a href="https://arxiv.org/pdf/2312.03989">pdf</a>, <a href="https://arxiv.org/format/2312.03989">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> </div> </div> <p class="title is-5 mathjax"> Rapid detection of rare events from in situ X-ray diffraction data using machine learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+W">Weijian Zheng</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jun-Sang Park</a>, <a href="/search/cs?searchtype=author&query=Kenesei%2C+P">Peter Kenesei</a>, <a href="/search/cs?searchtype=author&query=Ali%2C+A">Ahsan Ali</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhengchun Liu</a>, <a href="/search/cs?searchtype=author&query=Foster%2C+I+T">Ian T. Foster</a>, <a href="/search/cs?searchtype=author&query=Schwarz%2C+N">Nicholas Schwarz</a>, <a href="/search/cs?searchtype=author&query=Kettimuthu%2C+R">Rajkumar Kettimuthu</a>, <a href="/search/cs?searchtype=author&query=Miceli%2C+A">Antonino Miceli</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hemant Sharma</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.03989v1-abstract-short" style="display: inline;"> High-energy X-ray diffraction methods can non-destructively map the 3D microstructure and associated attributes of metallic polycrystalline engineering materials in their bulk form. These methods are often combined with external stimuli such as thermo-mechanical loading to take snapshots over time of the evolving microstructure and attributes. However, the extreme data volumes and the high costs o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.03989v1-abstract-full').style.display = 'inline'; document.getElementById('2312.03989v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.03989v1-abstract-full" style="display: none;"> High-energy X-ray diffraction methods can non-destructively map the 3D microstructure and associated attributes of metallic polycrystalline engineering materials in their bulk form. These methods are often combined with external stimuli such as thermo-mechanical loading to take snapshots over time of the evolving microstructure and attributes. However, the extreme data volumes and the high costs of traditional data acquisition and reduction approaches pose a barrier to quickly extracting actionable insights and improving the temporal resolution of these snapshots. Here we present a fully automated technique capable of rapidly detecting the onset of plasticity in high-energy X-ray microscopy data. Our technique is computationally faster by at least 50 times than the traditional approaches and works for data sets that are up to 9 times sparser than a full data set. This new technique leverages self-supervised image representation learning and clustering to transform massive data into compact, semantic-rich representations of visually salient characteristics (e.g., peak shapes). These characteristics can be a rapid indicator of anomalous events such as changes in diffraction peak shapes. We anticipate that this technique will provide just-in-time actionable information to drive smarter experiments that effectively deploy multi-modal X-ray diffraction methods that span many decades of length scales. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.03989v1-abstract-full').style.display = 'none'; document.getElementById('2312.03989v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.06158">arXiv:2311.06158</a> <span> [<a href="https://arxiv.org/pdf/2311.06158">pdf</a>, <a href="https://arxiv.org/format/2311.06158">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"> Language Models can be Logical Solvers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+J">Jiazhan Feng</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+R">Ruochen Xu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+J">Junheng Hao</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yelong Shen</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+D">Dongyan Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weizhu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.06158v1-abstract-short" style="display: inline;"> Logical reasoning is a fundamental aspect of human intelligence and a key component of tasks like problem-solving and decision-making. Recent advancements have enabled Large Language Models (LLMs) to potentially exhibit reasoning capabilities, but complex logical reasoning remains a challenge. The state-of-the-art, solver-augmented language models, use LLMs to parse natural language logical questi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.06158v1-abstract-full').style.display = 'inline'; document.getElementById('2311.06158v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.06158v1-abstract-full" style="display: none;"> Logical reasoning is a fundamental aspect of human intelligence and a key component of tasks like problem-solving and decision-making. Recent advancements have enabled Large Language Models (LLMs) to potentially exhibit reasoning capabilities, but complex logical reasoning remains a challenge. The state-of-the-art, solver-augmented language models, use LLMs to parse natural language logical questions into symbolic representations first and then adopt external logical solvers to take in the symbolic representations and output the answers. Despite their impressive performance, any parsing errors will inevitably result in the failure of the execution of the external logical solver and no answer to the logical questions. In this paper, we introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers and bypasses the parsing errors by learning to strict adherence to solver syntax and grammar. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers. Experimental results on two public deductive reasoning datasets demonstrate that LoGiPT outperforms state-of-the-art solver-augmented LMs and few-shot prompting methods on competitive LLMs like ChatGPT or GPT-4. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.06158v1-abstract-full').style.display = 'none'; document.getElementById('2311.06158v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.00995">arXiv:2311.00995</a> <span> [<a href="https://arxiv.org/pdf/2311.00995">pdf</a>, <a href="https://arxiv.org/ps/2311.00995">ps</a>, <a href="https://arxiv.org/format/2311.00995">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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hrishikesh Sharma</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="2311.00995v1-abstract-short" style="display: inline;"> Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.00995v1-abstract-full').style.display = 'inline'; document.getElementById('2311.00995v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.00995v1-abstract-full" style="display: none;"> Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN literature from various focus and perspectives. However, none of the surveys brings out the important chronological aspect: how the multiple challenges of employing GAN models were solved one-by-one over time, across multiple landmark research works. This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.00995v1-abstract-full').style.display = 'none'; document.getElementById('2311.00995v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.14573">arXiv:2310.14573</a> <span> [<a href="https://arxiv.org/pdf/2310.14573">pdf</a>, <a href="https://arxiv.org/format/2310.14573">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"> Exploring the Boundaries of GPT-4 in Radiology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qianchu Liu</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S">Stephanie Hyland</a>, <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M+T">Maria Teodora Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Tinn%2C+R">Robert Tinn</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Rajpurkar%2C+P">Pranav Rajpurkar</a>, <a href="/search/cs?searchtype=author&query=Khanna%2C+S+T">Sameer Tajdin Khanna</a>, <a href="/search/cs?searchtype=author&query=Poon%2C+H">Hoifung Poon</a>, <a href="/search/cs?searchtype=author&query=Usuyama%2C+N">Naoto Usuyama</a>, <a href="/search/cs?searchtype=author&query=Thieme%2C+A">Anja Thieme</a>, <a href="/search/cs?searchtype=author&query=Nori%2C+A+V">Aditya V. Nori</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</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="2310.14573v1-abstract-short" style="display: inline;"> The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14573v1-abstract-full').style.display = 'inline'; document.getElementById('2310.14573v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.14573v1-abstract-full" style="display: none;"> The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains ($\approx$ 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference ($F_1$). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain knowledge. For findings summarisation, GPT-4 outputs are found to be overall comparable with existing manually-written impressions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14573v1-abstract-full').style.display = 'none'; document.getElementById('2310.14573v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">EMNLP 2023 main</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.09932">arXiv:2310.09932</a> <span> [<a href="https://arxiv.org/pdf/2310.09932">pdf</a>, <a href="https://arxiv.org/format/2310.09932">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> "Reading Between the Heat": Co-Teaching Body Thermal Signatures for Non-intrusive Stress Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yi Xiao</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshit Sharma</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Bergen-Cico%2C+D">Dessa Bergen-Cico</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+T">Tauhidur Rahman</a>, <a href="/search/cs?searchtype=author&query=Salekin%2C+A">Asif Salekin</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="2310.09932v2-abstract-short" style="display: inline;"> Stress impacts our physical and mental health as well as our social life. A passive and contactless indoor stress monitoring system can unlock numerous important applications such as workplace productivity assessment, smart homes, and personalized mental health monitoring. While the thermal signatures from a user's body captured by a thermal camera can provide important information about the "figh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09932v2-abstract-full').style.display = 'inline'; document.getElementById('2310.09932v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.09932v2-abstract-full" style="display: none;"> Stress impacts our physical and mental health as well as our social life. A passive and contactless indoor stress monitoring system can unlock numerous important applications such as workplace productivity assessment, smart homes, and personalized mental health monitoring. While the thermal signatures from a user's body captured by a thermal camera can provide important information about the "fight-flight" response of the sympathetic and parasympathetic nervous system, relying solely on thermal imaging for training a stress prediction model often lead to overfitting and consequently a suboptimal performance. This paper addresses this challenge by introducing ThermaStrain, a novel co-teaching framework that achieves high-stress prediction performance by transferring knowledge from the wearable modality to the contactless thermal modality. During training, ThermaStrain incorporates a wearable electrodermal activity (EDA) sensor to generate stress-indicative representations from thermal videos, emulating stress-indicative representations from a wearable EDA sensor. During testing, only thermal sensing is used, and stress-indicative patterns from thermal data and emulated EDA representations are extracted to improve stress assessment. The study collected a comprehensive dataset with thermal video and EDA data under various stress conditions and distances. ThermaStrain achieves an F1 score of 0.8293 in binary stress classification, outperforming the thermal-only baseline approach by over 9%. Extensive evaluations highlight ThermaStrain's effectiveness in recognizing stress-indicative attributes, its adaptability across distances and stress scenarios, real-time executability on edge platforms, its applicability to multi-individual sensing, ability to function on limited visibility and unfamiliar conditions, and the advantages of its co-teaching approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09932v2-abstract-full').style.display = 'none'; document.getElementById('2310.09932v2-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">29 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/2309.15129">arXiv:2309.15129</a> <span> [<a href="https://arxiv.org/pdf/2309.15129">pdf</a>, <a href="https://arxiv.org/format/2309.15129">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Evaluating Cognitive Maps and Planning in Large Language Models with CogEval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Momennejad%2C+I">Ida Momennejad</a>, <a href="/search/cs?searchtype=author&query=Hasanbeig%2C+H">Hosein Hasanbeig</a>, <a href="/search/cs?searchtype=author&query=Vieira%2C+F">Felipe Vieira</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Ness%2C+R+O">Robert Osazuwa Ness</a>, <a href="/search/cs?searchtype=author&query=Jojic%2C+N">Nebojsa Jojic</a>, <a href="/search/cs?searchtype=author&query=Palangi%2C+H">Hamid Palangi</a>, <a href="/search/cs?searchtype=author&query=Larson%2C+J">Jonathan Larson</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="2309.15129v1-abstract-short" style="display: inline;"> Recently an influx of studies claim emergent cognitive abilities in large language models (LLMs). Yet, most rely on anecdotes, overlook contamination of training sets, or lack systematic Evaluation involving multiple tasks, control conditions, multiple iterations, and statistical robustness tests. Here we make two major contributions. First, we propose CogEval, a cognitive science-inspired protoco… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.15129v1-abstract-full').style.display = 'inline'; document.getElementById('2309.15129v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.15129v1-abstract-full" style="display: none;"> Recently an influx of studies claim emergent cognitive abilities in large language models (LLMs). Yet, most rely on anecdotes, overlook contamination of training sets, or lack systematic Evaluation involving multiple tasks, control conditions, multiple iterations, and statistical robustness tests. Here we make two major contributions. First, we propose CogEval, a cognitive science-inspired protocol for the systematic evaluation of cognitive capacities in Large Language Models. The CogEval protocol can be followed for the evaluation of various abilities. Second, here we follow CogEval to systematically evaluate cognitive maps and planning ability across eight LLMs (OpenAI GPT-4, GPT-3.5-turbo-175B, davinci-003-175B, Google Bard, Cohere-xlarge-52.4B, Anthropic Claude-1-52B, LLaMA-13B, and Alpaca-7B). We base our task prompts on human experiments, which offer both established construct validity for evaluating planning, and are absent from LLM training sets. We find that, while LLMs show apparent competence in a few planning tasks with simpler structures, systematic evaluation reveals striking failure modes in planning tasks, including hallucinations of invalid trajectories and getting trapped in loops. These findings do not support the idea of emergent out-of-the-box planning ability in LLMs. This could be because LLMs do not understand the latent relational structures underlying planning problems, known as cognitive maps, and fail at unrolling goal-directed trajectories based on the underlying structure. Implications for application and future directions are discussed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.15129v1-abstract-full').style.display = 'none'; document.getElementById('2309.15129v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.13701">arXiv:2309.13701</a> <span> [<a href="https://arxiv.org/pdf/2309.13701">pdf</a>, <a href="https://arxiv.org/format/2309.13701">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hasanbeig%2C+H">Hosein Hasanbeig</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Betthauser%2C+L">Leo Betthauser</a>, <a href="/search/cs?searchtype=author&query=Frujeri%2C+F+V">Felipe Vieira Frujeri</a>, <a href="/search/cs?searchtype=author&query=Momennejad%2C+I">Ida Momennejad</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="2309.13701v2-abstract-short" style="display: inline;"> From grading papers to summarizing medical documents, large language models (LLMs) are evermore used for evaluation of text generated by humans and AI alike. However, despite their extensive utility, LLMs exhibit distinct failure modes, necessitating a thorough audit and improvement of their text evaluation capabilities. Here we introduce ALLURE, a systematic approach to Auditing Large Language Mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.13701v2-abstract-full').style.display = 'inline'; document.getElementById('2309.13701v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.13701v2-abstract-full" style="display: none;"> From grading papers to summarizing medical documents, large language models (LLMs) are evermore used for evaluation of text generated by humans and AI alike. However, despite their extensive utility, LLMs exhibit distinct failure modes, necessitating a thorough audit and improvement of their text evaluation capabilities. Here we introduce ALLURE, a systematic approach to Auditing Large Language Models Understanding and Reasoning Errors. ALLURE involves comparing LLM-generated evaluations with annotated data, and iteratively incorporating instances of significant deviation into the evaluator, which leverages in-context learning (ICL) to enhance and improve robust evaluation of text by LLMs. Through this iterative process, we refine the performance of the evaluator LLM, ultimately reducing reliance on human annotators in the evaluation process. We anticipate ALLURE to serve diverse applications of LLMs in various domains related to evaluation of textual data, such as medical summarization, education, and and productivity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.13701v2-abstract-full').style.display = 'none'; document.getElementById('2309.13701v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.01697">arXiv:2309.01697</a> <span> [<a href="https://arxiv.org/pdf/2309.01697">pdf</a>, <a href="https://arxiv.org/format/2309.01697">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="Data Analysis, Statistics and Probability">physics.data-an</span> </div> </div> <p class="title is-5 mathjax"> Physics-Informed Polynomial Chaos Expansions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nov%C3%A1k%2C+L">Luk谩拧 Nov谩k</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Shields%2C+M+D">Michael D. Shields</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="2309.01697v1-abstract-short" style="display: inline;"> Surrogate modeling of costly mathematical models representing physical systems is challenging since it is typically not possible to create a large experimental design. Thus, it is beneficial to constrain the approximation to adhere to the known physics of the model. This paper presents a novel methodology for the construction of physics-informed polynomial chaos expansions (PCE) that combines the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.01697v1-abstract-full').style.display = 'inline'; document.getElementById('2309.01697v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.01697v1-abstract-full" style="display: none;"> Surrogate modeling of costly mathematical models representing physical systems is challenging since it is typically not possible to create a large experimental design. Thus, it is beneficial to constrain the approximation to adhere to the known physics of the model. This paper presents a novel methodology for the construction of physics-informed polynomial chaos expansions (PCE) that combines the conventional experimental design with additional constraints from the physics of the model. Physical constraints investigated in this paper are represented by a set of differential equations and specified boundary conditions. A computationally efficient means for construction of physically constrained PCE is proposed and compared to standard sparse PCE. It is shown that the proposed algorithms lead to superior accuracy of the approximation and does not add significant computational burden. Although the main purpose of the proposed method lies in combining data and physical constraints, we show that physically constrained PCEs can be constructed from differential equations and boundary conditions alone without requiring evaluations of the original model. We further show that the constrained PCEs can be easily applied for uncertainty quantification through analytical post-processing of a reduced PCE filtering out the influence of all deterministic space-time variables. Several deterministic examples of increasing complexity are provided and the proposed method is applied for uncertainty quantification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.01697v1-abstract-full').style.display = 'none'; document.getElementById('2309.01697v1-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.02231">arXiv:2306.02231</a> <span> [<a href="https://arxiv.org/pdf/2306.02231">pdf</a>, <a href="https://arxiv.org/format/2306.02231">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Fine-Tuning Language Models with Advantage-Induced Policy Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+B">Banghua Zhu</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hiteshi Sharma</a>, <a href="/search/cs?searchtype=author&query=Frujeri%2C+F+V">Felipe Vieira Frujeri</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+S">Shi Dong</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+C">Chenguang Zhu</a>, <a href="/search/cs?searchtype=author&query=Jordan%2C+M+I">Michael I. Jordan</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+J">Jiantao Jiao</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="2306.02231v3-abstract-short" style="display: inline;"> Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most widely used methods. Despite its popularity, however, PPO may suffer from mode collapse, instability, and poor sample efficiency. We show that these issues can be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02231v3-abstract-full').style.display = 'inline'; document.getElementById('2306.02231v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.02231v3-abstract-full" style="display: none;"> Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most widely used methods. Despite its popularity, however, PPO may suffer from mode collapse, instability, and poor sample efficiency. We show that these issues can be alleviated by a novel algorithm that we refer to as Advantage-Induced Policy Alignment (APA), which leverages a squared error loss function based on the estimated advantages. We demonstrate empirically that APA consistently outperforms PPO in language tasks by a large margin, when a separate reward model is employed as the evaluator. In addition, compared with PPO, APA offers a more stable form of control over the deviation from the model's initial policy, ensuring that the model improves its performance without collapsing to deterministic output. In addition to empirical results, we also provide a theoretical justification supporting the design of our loss function. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02231v3-abstract-full').style.display = 'none'; document.getElementById('2306.02231v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.15490">arXiv:2305.15490</a> <span> [<a href="https://arxiv.org/pdf/2305.15490">pdf</a>, <a href="https://arxiv.org/ps/2305.15490">ps</a>, <a href="https://arxiv.org/format/2305.15490">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</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="Mathematical Physics">math-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</span> </div> </div> <p class="title is-5 mathjax"> Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harsh Sharma</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+H">Hongliang Mu</a>, <a href="/search/cs?searchtype=author&query=Buchfink%2C+P">Patrick Buchfink</a>, <a href="/search/cs?searchtype=author&query=Geelen%2C+R">Rudy Geelen</a>, <a href="/search/cs?searchtype=author&query=Glas%2C+S">Silke Glas</a>, <a href="/search/cs?searchtype=author&query=Kramer%2C+B">Boris Kramer</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="2305.15490v2-abstract-short" style="display: inline;"> This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symplectic subspaces for representing the high-dimensional system states in a reduced-dimensional coordinate system. While these approximations respect the symplectic nature of Hamilto… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15490v2-abstract-full').style.display = 'inline'; document.getElementById('2305.15490v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.15490v2-abstract-full" style="display: none;"> This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symplectic subspaces for representing the high-dimensional system states in a reduced-dimensional coordinate system. While these approximations respect the symplectic nature of Hamiltonian systems, linear basis approximations can suffer from slowly decaying Kolmogorov $N$-width, especially in wave-type problems, which then requires a large basis size. We propose two different model reduction methods based on recently developed quadratic manifolds, each presenting its own advantages and limitations. The addition of quadratic terms to the state approximation, which sits at the heart of the proposed methodologies, enables us to better represent intrinsic low-dimensionality in the problem at hand. Both approaches are effective for issuing predictions in settings well outside the range of their training data while providing more accurate solutions than the linear symplectic reduced-order models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15490v2-abstract-full').style.display = 'none'; document.getElementById('2305.15490v2-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.09572">arXiv:2305.09572</a> <span> [<a href="https://arxiv.org/pdf/2305.09572">pdf</a>, <a href="https://arxiv.org/ps/2305.09572">ps</a>, <a href="https://arxiv.org/format/2305.09572">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> </div> </div> <p class="title is-5 mathjax"> UQpy v4.1: Uncertainty Quantification with Python </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tsapetis%2C+D">Dimitrios Tsapetis</a>, <a href="/search/cs?searchtype=author&query=Shields%2C+M+D">Michael D. Shields</a>, <a href="/search/cs?searchtype=author&query=Giovanis%2C+D+G">Dimitris G. Giovanis</a>, <a href="/search/cs?searchtype=author&query=Olivier%2C+A">Audrey Olivier</a>, <a href="/search/cs?searchtype=author&query=Novak%2C+L">Lukas Novak</a>, <a href="/search/cs?searchtype=author&query=Chakroborty%2C+P">Promit Chakroborty</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Chauhan%2C+M">Mohit Chauhan</a>, <a href="/search/cs?searchtype=author&query=Kontolati%2C+K">Katiana Kontolati</a>, <a href="/search/cs?searchtype=author&query=Vandanapu%2C+L">Lohit Vandanapu</a>, <a href="/search/cs?searchtype=author&query=Loukrezis%2C+D">Dimitrios Loukrezis</a>, <a href="/search/cs?searchtype=author&query=Gardner%2C+M">Michael Gardner</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="2305.09572v1-abstract-short" style="display: inline;"> This paper presents the latest improvements introduced in Version 4 of the UQpy, Uncertainty Quantification with Python, library. In the latest version, the code was restructured to conform with the latest Python coding conventions, refactored to simplify previous tightly coupled features, and improve its extensibility and modularity. To improve the robustness of UQpy, software engineering best pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09572v1-abstract-full').style.display = 'inline'; document.getElementById('2305.09572v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.09572v1-abstract-full" style="display: none;"> This paper presents the latest improvements introduced in Version 4 of the UQpy, Uncertainty Quantification with Python, library. In the latest version, the code was restructured to conform with the latest Python coding conventions, refactored to simplify previous tightly coupled features, and improve its extensibility and modularity. To improve the robustness of UQpy, software engineering best practices were adopted. A new software development workflow significantly improved collaboration between team members, and continous integration and automated testing ensured the robustness and reliability of software performance. Continuous deployment of UQpy allowed its automated packaging and distribution in system agnostic format via multiple channels, while a Docker image enables the use of the toolbox regardless of operating system limitations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09572v1-abstract-full').style.display = 'none'; document.getElementById('2305.09572v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.18135">arXiv:2303.18135</a> <span> [<a href="https://arxiv.org/pdf/2303.18135">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"> Towards A Sustainable and Ethical Supply Chain Management: The Potential of IoT Solutions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hardik Sharma</a>, <a href="/search/cs?searchtype=author&query=Garg%2C+R">Rajat Garg</a>, <a href="/search/cs?searchtype=author&query=Sewani%2C+H">Harshini Sewani</a>, <a href="/search/cs?searchtype=author&query=Kashef%2C+R">Rasha Kashef</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="2303.18135v1-abstract-short" style="display: inline;"> Globalization has introduced many new challenges making Supply chain management (SCM) complex and huge, for which improvement is needed in many industries. The Internet of Things (IoT) has solved many problems by providing security and traceability with a promising solution for supply chain management. SCM is segregated into different processes, each requiring different types of solutions. IoT dev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.18135v1-abstract-full').style.display = 'inline'; document.getElementById('2303.18135v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.18135v1-abstract-full" style="display: none;"> Globalization has introduced many new challenges making Supply chain management (SCM) complex and huge, for which improvement is needed in many industries. The Internet of Things (IoT) has solved many problems by providing security and traceability with a promising solution for supply chain management. SCM is segregated into different processes, each requiring different types of solutions. IoT devices can solve distributed system problems by creating trustful relationships. Since the whole business industry depends on the trust between different supply chain actors, IoT can provide this trust by making the entire ecosystem much more secure, reliable, and traceable. This paper will discuss how IoT technology has solved problems related to SCM in different areas. Supply chains in different industries, from pharmaceuticals to agriculture supply chain, have different issues and require different solutions. We will discuss problems such as security, tracking, traceability, and warehouse issues. All challenges faced by independent industries regarding the supply chain and how the amalgamation of IoT with other technology will be provided with solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.18135v1-abstract-full').style.display = 'none'; document.getElementById('2303.18135v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 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/2303.03483">arXiv:2303.03483</a> <span> [<a href="https://arxiv.org/pdf/2303.03483">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> In-Storage Domain-Specific Acceleration for Serverless Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mahapatra%2C+R">Rohan Mahapatra</a>, <a href="/search/cs?searchtype=author&query=Ghodrati%2C+S">Soroush Ghodrati</a>, <a href="/search/cs?searchtype=author&query=Ahn%2C+B+H">Byung Hoon Ahn</a>, <a href="/search/cs?searchtype=author&query=Kinzer%2C+S">Sean Kinzer</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shu-ting Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hanyang Xu</a>, <a href="/search/cs?searchtype=author&query=Karthikeyan%2C+L">Lavanya Karthikeyan</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Hardik Sharma</a>, <a href="/search/cs?searchtype=author&query=Yazdanbakhsh%2C+A">Amir Yazdanbakhsh</a>, <a href="/search/cs?searchtype=author&query=Alian%2C+M">Mohammad Alian</a>, <a href="/search/cs?searchtype=author&query=Esmaeilzadeh%2C+H">Hadi Esmaeilzadeh</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="2303.03483v2-abstract-short" style="display: inline;"> While (1) serverless computing is emerging as a popular form of cloud execution, datacenters are going through major changes: (2) storage dissaggregation in the system infrastructure level and (3) integration of domain-specific accelerators in the hardware level. Each of these three trends individually provide significant benefits; however, when combined the benefits diminish. Specifically, the pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.03483v2-abstract-full').style.display = 'inline'; document.getElementById('2303.03483v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.03483v2-abstract-full" style="display: none;"> While (1) serverless computing is emerging as a popular form of cloud execution, datacenters are going through major changes: (2) storage dissaggregation in the system infrastructure level and (3) integration of domain-specific accelerators in the hardware level. Each of these three trends individually provide significant benefits; however, when combined the benefits diminish. Specifically, the paper makes the key observation that for serverless functions, the overhead of accessing dissaggregated persistent storage overshadows the gains from accelerators. Therefore, to benefit from all these trends in conjunction, we propose Domain-Specific Computational Storage for Serverless (DSCS-Serverless). This idea contributes a serverless model that leverages a programmable accelerator within computational storage to conjugate the benefits of acceleration and storage disaggregation simultaneously. Our results with eight applications shows that integrating a comparatively small accelerator within the storage (DSCS-Serverless) that fits within its power constrains (15 Watts), significantly outperforms a traditional disaggregated system that utilizes the NVIDIA RTX 2080 Ti GPU (250 Watts). Further, the work highlights that disaggregation, serverless model, and the limited power budget for computation in storage require a different design than the conventional practices of integrating microprocessors and FPGAs. This insight is in contrast with current practices of designing computational storage that are yet to address the challenges associated with the shifts in datacenters. In comparison with two such conventional designs that either use quad-core ARM A57 or a Xilinx FPGA, DSCS-Serverless provides 3.7x and 1.7x end-to-end application speedup, 4.3x and 1.9x energy reduction, and 3.2x and 2.3x higher cost efficiency, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.03483v2-abstract-full').style.display = 'none'; document.getElementById('2303.03483v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.04558">arXiv:2301.04558</a> <span> [<a href="https://arxiv.org/pdf/2301.04558">pdf</a>, <a href="https://arxiv.org/format/2301.04558">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bannur%2C+S">Shruthi Bannur</a>, <a href="/search/cs?searchtype=author&query=Hyland%2C+S">Stephanie Hyland</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qianchu Liu</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Ilse%2C+M">Maximilian Ilse</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+D+C">Daniel C. Castro</a>, <a href="/search/cs?searchtype=author&query=Boecking%2C+B">Benedikt Boecking</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Harshita Sharma</a>, <a href="/search/cs?searchtype=author&query=Bouzid%2C+K">Kenza Bouzid</a>, <a href="/search/cs?searchtype=author&query=Thieme%2C+A">Anja Thieme</a>, <a href="/search/cs?searchtype=author&query=Schwaighofer%2C+A">Anton Schwaighofer</a>, <a href="/search/cs?searchtype=author&query=Wetscherek%2C+M">Maria Wetscherek</a>, <a href="/search/cs?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/cs?searchtype=author&query=Nori%2C+A">Aditya Nori</a>, <a href="/search/cs?searchtype=author&query=Alvarez-Valle%2C+J">Javier Alvarez-Valle</a>, <a href="/search/cs?searchtype=author&query=Oktay%2C+O">Ozan Oktay</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="2301.04558v2-abstract-short" style="display: inline;"> Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-superv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.04558v2-abstract-full').style.display = 'inline'; document.getElementById('2301.04558v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.04558v2-abstract-full" style="display: none;"> Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.04558v2-abstract-full').style.display = 'none'; document.getElementById('2301.04558v2-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in CVPR 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.10064">arXiv:2212.10064</a> <span> [<a href="https://arxiv.org/pdf/2212.10064">pdf</a>, <a href="https://arxiv.org/format/2212.10064">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+A">Aowabin Rahman</a>, <a href="/search/cs?searchtype=author&query=Bhattacharya%2C+A">Arnab Bhattacharya</a>, <a href="/search/cs?searchtype=author&query=Ramachandran%2C+T">Thiagarajan Ramachandran</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Fujimoto%2C+T">Ted Fujimoto</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Samrat Chatterjee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.10064v1-abstract-short" style="display: inline;"> Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration. Often, SAR coordination strategies are manually designed by human experts who can remotely control the multi-robot system and enable semi-a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.10064v1-abstract-full').style.display = 'inline'; document.getElementById('2212.10064v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.10064v1-abstract-full" style="display: none;"> Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration. Often, SAR coordination strategies are manually designed by human experts who can remotely control the multi-robot system and enable semi-autonomous operations. However, in remote environments where connectivity is limited and human intervention is often not possible, decentralized collaboration strategies are needed for fully-autonomous operations. Nevertheless, decentralized coordination may be ineffective in adversarial environments due to sensor noise, actuation faults, or manipulation of inter-agent communication data. In this paper, we propose an algorithmic approach based on adversarial multi-agent reinforcement learning (MARL) that allows robots to efficiently coordinate their strategies in the presence of adversarial inter-agent communications. In our setup, the objective of the multi-robot team is to discover targets strategically in an obstacle-strewn geographical area by minimizing the average time needed to find the targets. It is assumed that the robots have no prior knowledge of the target locations, and they can interact with only a subset of neighboring robots at any time. Based on the centralized training with decentralized execution (CTDE) paradigm in MARL, we utilize a hierarchical meta-learning framework to learn dynamic team-coordination modalities and discover emergent team behavior under complex cooperative-competitive scenarios. The effectiveness of our approach is demonstrated on a collection of prototype grid-world environments with different specifications of benign and adversarial agents, target locations, and agent rewards. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.10064v1-abstract-full').style.display = 'none'; document.getElementById('2212.10064v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </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=Sharma%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sharma%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sharma%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository