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 52 results for author: <span class="mathjax">Lyu, W</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=Lyu%2C+W">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="Lyu, W"> </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=Lyu%2C+W&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="Lyu, W"> <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=Lyu%2C+W&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lyu%2C+W&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lyu%2C+W&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/2412.04082">arXiv:2412.04082</a> <span> [<a href="https://arxiv.org/pdf/2412.04082">pdf</a>, <a href="https://arxiv.org/format/2412.04082">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"> Learnable Similarity and Dissimilarity Guided Symmetric Non-Negative Matrix Factorization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+Y">Yuheng Jia</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.04082v1-abstract-short" style="display: inline;"> Symmetric nonnegative matrix factorization (SymNMF) is a powerful tool for clustering, which typically uses the $k$-nearest neighbor ($k$-NN) method to construct similarity matrix. However, $k$-NN may mislead clustering since the neighbors may belong to different clusters, and its reliability generally decreases as $k$ grows. In this paper, we construct the similarity matrix as a weighted $k$-NN g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04082v1-abstract-full').style.display = 'inline'; document.getElementById('2412.04082v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04082v1-abstract-full" style="display: none;"> Symmetric nonnegative matrix factorization (SymNMF) is a powerful tool for clustering, which typically uses the $k$-nearest neighbor ($k$-NN) method to construct similarity matrix. However, $k$-NN may mislead clustering since the neighbors may belong to different clusters, and its reliability generally decreases as $k$ grows. In this paper, we construct the similarity matrix as a weighted $k$-NN graph with learnable weight that reflects the reliability of each $k$-th NN. This approach reduces the search space of the similarity matrix learning to $n - 1$ dimension, as opposed to the $\mathcal{O}(n^2)$ dimension of existing methods, where $n$ represents the number of samples. Moreover, to obtain a discriminative similarity matrix, we introduce a dissimilarity matrix with a dual structure of the similarity matrix, and propose a new form of orthogonality regularization with discussions on its geometric interpretation and numerical stability. An efficient alternative optimization algorithm is designed to solve the proposed model, with theoretically guarantee that the variables converge to a stationary point that satisfies the KKT conditions. The advantage of the proposed model is demonstrated by the comparison with nine state-of-the-art clustering methods on eight datasets. The code is available at \url{https://github.com/lwl-learning/LSDGSymNMF}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04082v1-abstract-full').style.display = 'none'; document.getElementById('2412.04082v1-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> 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 14 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05172">arXiv:2411.05172</a> <span> [<a href="https://arxiv.org/pdf/2411.05172">pdf</a>, <a href="https://arxiv.org/format/2411.05172">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"> ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Language </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuxin Wang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xiaomeng Zhu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Hassanpour%2C+S">Saeed Hassanpour</a>, <a href="/search/cs?searchtype=author&query=Vosoughi%2C+S">Soroush Vosoughi</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="2411.05172v2-abstract-short" style="display: inline;"> Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring the implicitness of language significantly constrains the depth of analysis possible in evaluating models' comprehension capabilities. This paper addresses this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05172v2-abstract-full').style.display = 'inline'; document.getElementById('2411.05172v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05172v2-abstract-full" style="display: none;"> Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring the implicitness of language significantly constrains the depth of analysis possible in evaluating models' comprehension capabilities. This paper addresses this gap by developing a scalar metric that quantifies the implicitness level of language without relying on external references. Drawing on principles from traditional linguistics, we define ''implicitness'' as the divergence between semantic meaning and pragmatic interpretation. To operationalize this definition, we introduce ImpScore, a novel, reference-free metric formulated through an interpretable regression model. This model is trained using pairwise contrastive learning on a specially curated dataset comprising $112,580$ (implicit sentence, explicit sentence) pairs. We validate ImpScore through a user study that compares its assessments with human evaluations on out-of-distribution data, demonstrating its accuracy and strong correlation with human judgments. Additionally, we apply ImpScore to hate speech detection datasets, illustrating its utility and highlighting significant limitations in current large language models' ability to understand highly implicit content. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05172v2-abstract-full').style.display = 'none'; document.getElementById('2411.05172v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12955">arXiv:2410.12955</a> <span> [<a href="https://arxiv.org/pdf/2410.12955">pdf</a>, <a href="https://arxiv.org/format/2410.12955">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pang%2C+L">Lu Pang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tao Sun</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2410.12955v1-abstract-short" style="display: inline;"> Recently, backdoor attack has become an increasing security threat to deep neural networks and drawn the attention of researchers. Backdoor attacks exploit vulnerabilities in third-party pretrained models during the training phase, enabling them to behave normally for clean samples and mispredict for samples with specific triggers. Existing backdoor attacks mainly focus on balanced datasets. Howev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12955v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12955v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12955v1-abstract-full" style="display: none;"> Recently, backdoor attack has become an increasing security threat to deep neural networks and drawn the attention of researchers. Backdoor attacks exploit vulnerabilities in third-party pretrained models during the training phase, enabling them to behave normally for clean samples and mispredict for samples with specific triggers. Existing backdoor attacks mainly focus on balanced datasets. However, real-world datasets often follow long-tailed distributions. In this paper, for the first time, we explore backdoor attack on such datasets. Specifically, we first analyze the influence of data imbalance on backdoor attack. Based on our analysis, we propose an effective backdoor attack named Dynamic Data Augmentation Operation (D$^2$AO). We design D$^2$AO selectors to select operations depending jointly on the class, sample type (clean vs. backdoored) and sample features. Meanwhile, we develop a trigger generator to generate sample-specific triggers. Through simultaneous optimization of the backdoored model and trigger generator, guided by dynamic data augmentation operation selectors, we achieve significant advancements. Extensive experiments demonstrate that our method can achieve the state-of-the-art attack performance while preserving the clean accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12955v1-abstract-full').style.display = 'none'; document.getElementById('2410.12955v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.01264">arXiv:2410.01264</a> <span> [<a href="https://arxiv.org/pdf/2410.01264">pdf</a>, <a href="https://arxiv.org/format/2410.01264">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"> Backdooring Vision-Language Models with Out-Of-Distribution Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+J">Jiachen Yao</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+S">Saumya Gupta</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+L">Lu Pang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tao Sun</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+L">Lingjie Yi</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L">Lijie Hu</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2410.01264v1-abstract-short" style="display: inline;"> The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the security of VLMs, particularly against backdoor attacks, is under explored. Moreover, prior works often assume attackers have access to the original train… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01264v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01264v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01264v1-abstract-full" style="display: none;"> The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the security of VLMs, particularly against backdoor attacks, is under explored. Moreover, prior works often assume attackers have access to the original training data, which is often unrealistic. In this paper, we address a more practical and challenging scenario where attackers must rely solely on Out-Of-Distribution (OOD) data. We introduce VLOOD (Backdooring Vision-Language Models with Out-of-Distribution Data), a novel approach with two key contributions: (1) demonstrating backdoor attacks on VLMs in complex image-to-text tasks while minimizing degradation of the original semantics under poisoned inputs, and (2) proposing innovative techniques for backdoor injection without requiring any access to the original training data. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of VLOOD, revealing a critical security vulnerability in VLMs and laying the foundation for future research on securing multimodal models against sophisticated threats. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01264v1-abstract-full').style.display = 'none'; document.getElementById('2410.01264v1-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 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/2409.19232">arXiv:2409.19232</a> <span> [<a href="https://arxiv.org/pdf/2409.19232">pdf</a>, <a href="https://arxiv.org/format/2409.19232">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"> TrojVLM: Backdoor Attack Against Vision Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+L">Lu Pang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tengfei Ma</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2409.19232v1-abstract-short" style="display: inline;"> The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attack… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19232v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19232v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19232v1-abstract-full" style="display: none;"> The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation. Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic preserving loss is proposed to ensure the semantic integrity of the original image content. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of TrojVLM in maintaining original semantic content while triggering specific target text outputs. This study not only uncovers a critical security risk in VLMs and image-to-text generation but also sets a foundation for future research on securing multimodal models against such sophisticated threats. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19232v1-abstract-full').style.display = 'none'; document.getElementById('2409.19232v1-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 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">ECCV 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18794">arXiv:2409.18794</a> <span> [<a href="https://arxiv.org/pdf/2409.18794">pdf</a>, <a href="https://arxiv.org/format/2409.18794">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yanyuan Qiao</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenqi Lyu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hui Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zixu Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zerui Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+M">Mingkui Tan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qi Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.18794v1-abstract-short" style="display: inline;"> Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closed-source large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges relate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18794v1-abstract-full').style.display = 'inline'; document.getElementById('2409.18794v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18794v1-abstract-full" style="display: none;"> Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closed-source large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in real-world applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18794v1-abstract-full').style.display = 'none'; document.getElementById('2409.18794v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08519">arXiv:2409.08519</a> <span> [<a href="https://arxiv.org/pdf/2409.08519">pdf</a>, <a href="https://arxiv.org/format/2409.08519">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Geometry">cs.CG</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/TVCG.2024.3456383">10.1109/TVCG.2024.3456383 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fast Comparative Analysis of Merge Trees Using Locality Sensitive Hashing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weiran Lyu</a>, <a href="/search/cs?searchtype=author&query=Sridharamurthy%2C+R">Raghavendra Sridharamurthy</a>, <a href="/search/cs?searchtype=author&query=Phillips%2C+J+M">Jeff M. Phillips</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bei 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="2409.08519v1-abstract-short" style="display: inline;"> Scalar field comparison is a fundamental task in scientific visualization. In topological data analysis, we compare topological descriptors of scalar fields -- such as persistence diagrams and merge trees -- because they provide succinct and robust abstract representations. Several similarity measures for topological descriptors seem to be both asymptotically and practically efficient with polynom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08519v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08519v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08519v1-abstract-full" style="display: none;"> Scalar field comparison is a fundamental task in scientific visualization. In topological data analysis, we compare topological descriptors of scalar fields -- such as persistence diagrams and merge trees -- because they provide succinct and robust abstract representations. Several similarity measures for topological descriptors seem to be both asymptotically and practically efficient with polynomial time algorithms, but they do not scale well when handling large-scale, time-varying scientific data and ensembles. In this paper, we propose a new framework to facilitate the comparative analysis of merge trees, inspired by tools from locality sensitive hashing (LSH). LSH hashes similar objects into the same hash buckets with high probability. We propose two new similarity measures for merge trees that can be computed via LSH, using new extensions to Recursive MinHash and subpath signature, respectively. Our similarity measures are extremely efficient to compute and closely resemble the results of existing measures such as merge tree edit distance or geometric interleaving distance. Our experiments demonstrate the utility of our LSH framework in applications such as shape matching, clustering, key event detection, and ensemble summarization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08519v1-abstract-full').style.display = 'none'; document.getElementById('2409.08519v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEEE VIS 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/2409.07388">arXiv:2409.07388</a> <span> [<a href="https://arxiv.org/pdf/2409.07388">pdf</a>, <a href="https://arxiv.org/format/2409.07388">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"> Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+G">Guimin Hu</a>, <a href="/search/cs?searchtype=author&query=Xin%2C+Y">Yi Xin</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Haojian Huang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+C">Chang Sun</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhihong Zhu</a>, <a href="/search/cs?searchtype=author&query=Gui%2C+L">Lin Gui</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+R">Ruichu Cai</a>, <a href="/search/cs?searchtype=author&query=Cambria%2C+E">Erik Cambria</a>, <a href="/search/cs?searchtype=author&query=Seifi%2C+H">Hasti Seifi</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="2409.07388v2-abstract-short" style="display: inline;"> Multimodal affective computing (MAC) has garnered increasing attention due to its broad applications in analyzing human behaviors and intentions, especially in text-dominated multimodal affective computing field. This survey presents the recent trends of multimodal affective computing from NLP perspective through four hot tasks: multimodal sentiment analysis, multimodal emotion recognition in conv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07388v2-abstract-full').style.display = 'inline'; document.getElementById('2409.07388v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07388v2-abstract-full" style="display: none;"> Multimodal affective computing (MAC) has garnered increasing attention due to its broad applications in analyzing human behaviors and intentions, especially in text-dominated multimodal affective computing field. This survey presents the recent trends of multimodal affective computing from NLP perspective through four hot tasks: multimodal sentiment analysis, multimodal emotion recognition in conversation, multimodal aspect-based sentiment analysis and multimodal multi-label emotion recognition. The goal of this survey is to explore the current landscape of multimodal affective research, identify development trends, and highlight the similarities and differences across various tasks, offering a comprehensive report on the recent progress in multimodal affective computing from an NLP perspective. This survey covers the formalization of tasks, provides an overview of relevant works, describes benchmark datasets, and details the evaluation metrics for each task. Additionally, it briefly discusses research in multimodal affective computing involving facial expressions, acoustic signals, physiological signals, and emotion causes. Additionally, we discuss the technical approaches, challenges, and future directions in multimodal affective computing. To support further research, we released a repository that compiles related works in multimodal affective computing, providing detailed resources and references for the community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07388v2-abstract-full').style.display = 'none'; document.getElementById('2409.07388v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.06505">arXiv:2407.06505</a> <span> [<a href="https://arxiv.org/pdf/2407.06505">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Not all explicit cues help communicate: Pedestrians' perceptions, fixations, and decisions toward automated vehicles with varied appearance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wei Lyu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yaqin Cao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yi Ding</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jingyu Li</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+K">Kai Tian</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.06505v1-abstract-short" style="display: inline;"> Given pedestrians' vulnerability in road traffic, it remains unclear how novel AV appearances will impact pedestrians crossing behaviour. To address this gap, this study pioneers an investigation into the influence of AVs' exterior design, correlated with their kinematics, on pedestrians' road-crossing perception and decision-making. A video-based eye-tracking experimental study was conducted with… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06505v1-abstract-full').style.display = 'inline'; document.getElementById('2407.06505v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.06505v1-abstract-full" style="display: none;"> Given pedestrians' vulnerability in road traffic, it remains unclear how novel AV appearances will impact pedestrians crossing behaviour. To address this gap, this study pioneers an investigation into the influence of AVs' exterior design, correlated with their kinematics, on pedestrians' road-crossing perception and decision-making. A video-based eye-tracking experimental study was conducted with 61 participants who responded to video stimuli depicting a manipulated vehicle approaching a predefined road-crossing location on an unsignalized, two-way road. The vehicle's kinematic pattern was manipulated into yielding and non-yielding, and its external appearances were varied across five types: with a human driver (as a conventional vehicle), with no driver (as an AV), with text-based identity indications, with roof radar sensors, with dynamic eHMIs adjusted to vehicle kinematics. Participants' perceived clarity, crossing initiation distance (CID), crossing decision time (CDT), and gaze behaviour, during interactions were recorded and reported. The results indicated that AVs' kinematic profiles play a dominant role in pedestrians' road-crossing decisions, supported by their subjective evaluations, CID, CDT, and gaze patterns during interactions. Moreover, the use of clear eHMI, such as dynamic pedestrian icons, reduced pedestrians' visual load, enhanced their perceptual clarity, expedited road-crossing decisions, and thereby improved overall crossing efficiency. However, it was found that both textual identity indications and roof radar sensors have no significant effect on pedestrians' decisions but negatively impact pedestrians' visual attention, as evidenced by heightened fixation counts and prolonged fixation durations, particularly under yielding conditions. Excessive visual and cognitive resource occupation suggests that not all explicit cues facilitate human-vehicle communication. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06505v1-abstract-full').style.display = 'none'; document.getElementById('2407.06505v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">37 pages, 13 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.05213">arXiv:2407.05213</a> <span> [<a href="https://arxiv.org/pdf/2407.05213">pdf</a>, <a href="https://arxiv.org/format/2407.05213">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"> BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Records </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Bi%2C+Z">Zexin Bi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fusheng Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2407.05213v1-abstract-short" style="display: inline;"> The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their success, the potential vulnerabilities of these models remain largely unexplored. This paper delves into the realm of backdoor attacks on clinical language models… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05213v1-abstract-full').style.display = 'inline'; document.getElementById('2407.05213v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05213v1-abstract-full" style="display: none;"> The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their success, the potential vulnerabilities of these models remain largely unexplored. This paper delves into the realm of backdoor attacks on clinical language models, introducing an innovative attention-based backdoor attack method, BadCLM (Bad Clinical Language Models). This technique clandestinely embeds a backdoor within the models, causing them to produce incorrect predictions when a pre-defined trigger is present in inputs, while functioning accurately otherwise. We demonstrate the efficacy of BadCLM through an in-hospital mortality prediction task with MIMIC III dataset, showcasing its potential to compromise model integrity. Our findings illuminate a significant security risk in clinical decision support systems and pave the way for future endeavors in fortifying clinical language models against such vulnerabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05213v1-abstract-full').style.display = 'none'; document.getElementById('2407.05213v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">AMIA 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04944">arXiv:2407.04944</a> <span> [<a href="https://arxiv.org/pdf/2407.04944">pdf</a>, <a href="https://arxiv.org/format/2407.04944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Flexible Antenna Arrays for Wireless Communications: Modeling and Performance Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=An%2C+J">Jiancheng An</a>, <a href="/search/cs?searchtype=author&query=Xiu%2C+Y">Yue Xiu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+B">Boyu Ning</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Debbah%2C+M">Merouane Debbah</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2407.04944v1-abstract-short" style="display: inline;"> Flexible antenna arrays (FAAs), distinguished by their rotatable, bendable, and foldable properties, are extensively employed in flexible radio systems to achieve customized radiation patterns. This paper aims to illustrate that FAAs, capable of dynamically adjusting surface shapes, can enhance communication performances with both omni-directional and directional antenna patterns, in terms of mult… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04944v1-abstract-full').style.display = 'inline'; document.getElementById('2407.04944v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04944v1-abstract-full" style="display: none;"> Flexible antenna arrays (FAAs), distinguished by their rotatable, bendable, and foldable properties, are extensively employed in flexible radio systems to achieve customized radiation patterns. This paper aims to illustrate that FAAs, capable of dynamically adjusting surface shapes, can enhance communication performances with both omni-directional and directional antenna patterns, in terms of multi-path channel power and channel angle Cram茅r-Rao bounds. To this end, we develop a mathematical model that elucidates the impacts of the variations in antenna positions and orientations as the array transitions from a flat to a rotated, bent, and folded state, all contingent on the flexible degree-of-freedom. Moreover, since the array shape adjustment operates across the entire beamspace, especially with directional patterns, we discuss the sum-rate in the multi-sector base station that covers the $360^\circ$ communication area. Particularly, to thoroughly explore the multi-sector sum-rate, we propose separate flexible precoding (SFP), joint flexible precoding (JFP), and semi-joint flexible precoding (SJFP), respectively. In our numerical analysis comparing the optimized FAA to the fixed uniform planar array, we find that the bendable FAA achieves a remarkable $156\%$ sum-rate improvement compared to the fixed planar array in the case of JFP with the directional pattern. Furthermore, the rotatable FAA exhibits notably superior performance in SFP and SJFP cases with omni-directional patterns, with respective $35\%$ and $281\%$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04944v1-abstract-full').style.display = 'none'; document.getElementById('2407.04944v1-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 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/2406.05452">arXiv:2406.05452</a> <span> [<a href="https://arxiv.org/pdf/2406.05452">pdf</a>, <a href="https://arxiv.org/format/2406.05452">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Near-Field Channel Estimation for Extremely Large-Scale Terahertz Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Y">Yizhou Peng</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Ya Li</a>, <a href="/search/cs?searchtype=author&query=He%2C+H">Hongjun He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2406.05452v1-abstract-short" style="display: inline;"> Future Terahertz communications exhibit significant potential in accommodating ultra-high-rate services. Employing extremely large-scale array antennas is a key approach to realize this potential, as they can harness substantial beamforming gains to overcome the severe path loss and leverage the electromagnetic advantages in the near field. This paper proposes novel estimation methods designed to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05452v1-abstract-full').style.display = 'inline'; document.getElementById('2406.05452v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05452v1-abstract-full" style="display: none;"> Future Terahertz communications exhibit significant potential in accommodating ultra-high-rate services. Employing extremely large-scale array antennas is a key approach to realize this potential, as they can harness substantial beamforming gains to overcome the severe path loss and leverage the electromagnetic advantages in the near field. This paper proposes novel estimation methods designed to enhance efficiency in Terahertz widely-spaced multi-subarray (WSMS) systems. Initially, we introduce three sparse channel representation methods: polar-domain representation (PD-R), multi-angular-domain representation (MAD-R), and two-dimensional polar-angular-domain representation (2D-PAD-R). Each method is meticulously developed for near-field WSMS channels, capitalizing on their sparsity characteristics. Building on this, we propose four estimation frameworks using the sparse recovery theory: polar-domain estimation (PD-E), multi-angular-domain estimation (MAD-E), two-stage polar-angular-domain estimation (TS-PAD-E), and two-dimensional polar-angular-domain estimation (2D-PAD-E). Particularly, 2D-PAD-E, integrating a 2D dictionary process, and TS-PAD-E, with its sequential approach to angle and distance estimation, stand out as particularly effective for near-field angle-distance estimation, enabling decoupled calculation of these parameters. Overall, these frameworks provide versatile and efficient solutions for WSMS channel estimation, balancing low complexity with high-performance outcomes. Additionally, they represent a fresh perspective on near-field signal processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05452v1-abstract-full').style.display = 'none'; document.getElementById('2406.05452v1-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 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/2406.05392">arXiv:2406.05392</a> <span> [<a href="https://arxiv.org/pdf/2406.05392">pdf</a>, <a href="https://arxiv.org/format/2406.05392">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="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deng%2C+C">Chengyuan Deng</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+Y">Yiqun Duan</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+X">Xin Jin</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+H">Heng Chang</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Y">Yijun Tian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Han Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yichen Wang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+K">Kuofeng Gao</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+H+P">Henry Peng Zou</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Y">Yiqiao Jin</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yijia Xiao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shenghao Wu</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Z">Zongxing Xie</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=He%2C+S">Sihong He</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Lu Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haohan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+J">Jun Zhuang</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="2406.05392v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns, impacting the deployment of LLMs in everyday contexts. This paper provides a comprehensive survey of ethical challenges associated with LLMs, from longstanding issues such as copyright infringement, systematic bias, an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05392v2-abstract-full').style.display = 'inline'; document.getElementById('2406.05392v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05392v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns, impacting the deployment of LLMs in everyday contexts. This paper provides a comprehensive survey of ethical challenges associated with LLMs, from longstanding issues such as copyright infringement, systematic bias, and data privacy, to emerging problems like truthfulness and social norms. We critically analyze existing research aimed at understanding, examining, and mitigating these ethical risks. Our survey underscores integrating ethical standards and societal values into the development of LLMs, thereby guiding the development of responsible and ethically aligned language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05392v2-abstract-full').style.display = 'none'; document.getElementById('2406.05392v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 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/2404.13414">arXiv:2404.13414</a> <span> [<a href="https://arxiv.org/pdf/2404.13414">pdf</a>, <a href="https://arxiv.org/format/2404.13414">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/10.1145/3657604.3662036">10.1145/3657604.3662036 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Evaluating the Effectiveness of LLMs in Introductory Computer Science Education: A Semester-Long Field Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenhan Lyu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yimeng Wang</a>, <a href="/search/cs?searchtype=author&query=Tingting"> Tingting</a>, <a href="/search/cs?searchtype=author&query=Chung"> Chung</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yifan Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yixuan Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.13414v3-abstract-short" style="display: inline;"> The integration of AI assistants, especially through the development of Large Language Models (LLMs), into computer science education has sparked significant debate. An emerging body of work has looked into using LLMs in education, but few have examined the impacts of LLMs on students in entry-level programming courses, particularly in real-world contexts and over extended periods. To address this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.13414v3-abstract-full').style.display = 'inline'; document.getElementById('2404.13414v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.13414v3-abstract-full" style="display: none;"> The integration of AI assistants, especially through the development of Large Language Models (LLMs), into computer science education has sparked significant debate. An emerging body of work has looked into using LLMs in education, but few have examined the impacts of LLMs on students in entry-level programming courses, particularly in real-world contexts and over extended periods. To address this research gap, we conducted a semester-long, between-subjects study with 50 students using CodeTutor, an LLM-powered assistant developed by our research team. Our study results show that students who used CodeTutor (the experimental group) achieved statistically significant improvements in their final scores compared to peers who did not use the tool (the control group). Within the experimental group, those without prior experience with LLM-powered tools demonstrated significantly greater performance gain than their counterparts. We also found that students expressed positive feedback regarding CodeTutor's capability, though they also had concerns about CodeTutor's limited role in developing critical thinking skills. Over the semester, students' agreement with CodeTutor's suggestions decreased, with a growing preference for support from traditional human teaching assistants. Our analysis further reveals that the quality of user prompts was significantly correlated with CodeTutor's response effectiveness. Building upon our results, we discuss the implications of our findings for integrating Generative AI literacy into curricula to foster critical thinking skills and turn to examining the temporal dynamics of user engagement with LLM-powered tools. We further discuss the discrepancy between the anticipated functions of tools and students' actual capabilities, which sheds light on the need for tailored strategies to improve educational outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.13414v3-abstract-full').style.display = 'none'; document.getElementById('2404.13414v3-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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">Accepted to Learning @ Scale 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07977">arXiv:2404.07977</a> <span> [<a href="https://arxiv.org/pdf/2404.07977">pdf</a>, <a href="https://arxiv.org/format/2404.07977">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"> Gaga: Group Any Gaussians via 3D-aware Memory Bank </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xueting Li</a>, <a href="/search/cs?searchtype=author&query=Kundu%2C+A">Abhijit Kundu</a>, <a href="/search/cs?searchtype=author&query=Tsai%2C+Y">Yi-Hsuan Tsai</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Ming-Hsuan Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07977v1-abstract-short" style="display: inline;"> We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot segmentation models. Contrasted to prior 3D scene segmentation approaches that heavily rely on video object tracking, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses. By eliminating the assumption of cont… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07977v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07977v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07977v1-abstract-full" style="display: none;"> We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot segmentation models. Contrasted to prior 3D scene segmentation approaches that heavily rely on video object tracking, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial for sparsely sampled images, ensuring precise mask label consistency. Furthermore, Gaga accommodates 2D segmentation masks from diverse sources and demonstrates robust performance with different open-world zero-shot segmentation models, enhancing its versatility. Extensive qualitative and quantitative evaluations demonstrate that Gaga performs favorably against state-of-the-art methods, emphasizing its potential for real-world applications such as scene understanding and manipulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07977v1-abstract-full').style.display = 'none'; document.getElementById('2404.07977v1-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 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">Project Page: https://www.gaga.gallery</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.00489">arXiv:2404.00489</a> <span> [<a href="https://arxiv.org/pdf/2404.00489">pdf</a>, <a href="https://arxiv.org/format/2404.00489">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ali%2C+M+A">Muhammad Asif Ali</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhengping Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shu Yang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+K">Keyuan Cheng</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yang Cao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+T">Tianhao Huang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+G">Guimin Hu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L">Lijie Hu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Lu Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Di 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="2404.00489v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to substandard results in terms of readability/interpretability of the compressed promp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00489v2-abstract-full').style.display = 'inline'; document.getElementById('2404.00489v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00489v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to substandard results in terms of readability/interpretability of the compressed prompt, with a detrimental impact on prompt utility. To address this, we propose PromptSAW: Prompt compresSion via Relation AWare graphs, an effective strategy for prompt compression over task-agnostic and task-aware prompts. Prompt-SAW uses the prompt's textual information to build a graph and later extracts key information elements in the graph to come up with the compressed prompt. We also propose GSM8K-aug, i.e., an extended version of the existing GSM8K benchmark for task-agnostic prompts in order to provide a comprehensive evaluation platform. Experimental evaluation using benchmark datasets shows that prompts compressed by Prompt-SAW are not only better in terms of readability, but they also outperform the best-performing baseline models by up to 10.1 and 77.1, respectively, for task-agnostic and task-aware settings while compressing the original prompt text by 34.9 and 56.7. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00489v2-abstract-full').style.display = 'none'; document.getElementById('2404.00489v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 March, 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">16 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/2403.17155">arXiv:2403.17155</a> <span> [<a href="https://arxiv.org/pdf/2403.17155">pdf</a>, <a href="https://arxiv.org/format/2403.17155">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Task-Agnostic Detector for Insertion-Based Backdoor Attacks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+X">Xiao Lin</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Songzhu Zheng</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+L">Lu Pang</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Jha%2C+S">Susmit Jha</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2403.17155v1-abstract-short" style="display: inline;"> Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence classification, struggling with tasks like question answering and named entity recognition. We introduce TABDet (Task-Agnostic Backdoor Detector), a pioneering ta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17155v1-abstract-full').style.display = 'inline'; document.getElementById('2403.17155v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17155v1-abstract-full" style="display: none;"> Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence classification, struggling with tasks like question answering and named entity recognition. We introduce TABDet (Task-Agnostic Backdoor Detector), a pioneering task-agnostic method for backdoor detection. TABDet leverages final layer logits combined with an efficient pooling technique, enabling unified logit representation across three prominent NLP tasks. TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional task-specific methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17155v1-abstract-full').style.display = 'none'; document.getElementById('2403.17155v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 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">Findings of NAACL 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/2402.18847">arXiv:2402.18847</a> <span> [<a href="https://arxiv.org/pdf/2402.18847">pdf</a>, <a href="https://arxiv.org/format/2402.18847">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> <div 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/LWC.2024.3372569">10.1109/LWC.2024.3372569 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Flexible Precoding for Multi-User Movable Antenna Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+B">Boyu Ning</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2402.18847v1-abstract-short" style="display: inline;"> This letter rethinks traditional precoding in multi-user wireless communications with movable antennas (MAs). Utilizing MAs for optimal antenna positioning, we introduce a sparse optimization (SO)-based approach focusing on regularized zero-forcing (RZF). This framework targets the optimization of antenna positions and the precoding matrix to minimize inter-user interference and transmit power. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18847v1-abstract-full').style.display = 'inline'; document.getElementById('2402.18847v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.18847v1-abstract-full" style="display: none;"> This letter rethinks traditional precoding in multi-user wireless communications with movable antennas (MAs). Utilizing MAs for optimal antenna positioning, we introduce a sparse optimization (SO)-based approach focusing on regularized zero-forcing (RZF). This framework targets the optimization of antenna positions and the precoding matrix to minimize inter-user interference and transmit power. We propose an off-grid regularized least squares-based orthogonal matching pursuit (RLS-OMP) method for this purpose. Moreover, we provide deeper insights into antenna position optimization using RLS-OMP, viewed from a subspace projection angle. Overall, our proposed flexible precoding scheme demonstrates a sum rate that exceeds more than twice that of fixed antenna positions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18847v1-abstract-full').style.display = 'none'; document.getElementById('2402.18847v1-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 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">Journal ref:</span> IEEE Wireless Communications Letters (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.09923">arXiv:2402.09923</a> <span> [<a href="https://arxiv.org/pdf/2402.09923">pdf</a>, <a href="https://arxiv.org/format/2402.09923">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"> A Dataset of Open-Domain Question Answering with Multiple-Span Answers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Zhiyi Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yingying Zhang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shuyun Luo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Ying Zhao</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wentao Lyu</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="2402.09923v1-abstract-short" style="display: inline;"> Multi-span answer extraction, also known as the task of multi-span question answering (MSQA), is critical for real-world applications, as it requires extracting multiple pieces of information from a text to answer complex questions. Despite the active studies and rapid progress in English MSQA research, there is a notable lack of publicly available MSQA benchmark in Chinese. Previous efforts for c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09923v1-abstract-full').style.display = 'inline'; document.getElementById('2402.09923v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.09923v1-abstract-full" style="display: none;"> Multi-span answer extraction, also known as the task of multi-span question answering (MSQA), is critical for real-world applications, as it requires extracting multiple pieces of information from a text to answer complex questions. Despite the active studies and rapid progress in English MSQA research, there is a notable lack of publicly available MSQA benchmark in Chinese. Previous efforts for constructing MSQA datasets predominantly emphasized entity-centric contextualization, resulting in a bias towards collecting factoid questions and potentially overlooking questions requiring more detailed descriptive responses. To overcome these limitations, we present CLEAN, a comprehensive Chinese multi-span question answering dataset that involves a wide range of open-domain subjects with a substantial number of instances requiring descriptive answers. Additionally, we provide established models from relevant literature as baselines for CLEAN. Experimental results and analysis show the characteristics and challenge of the newly proposed CLEAN dataset for the community. Our dataset, CLEAN, will be publicly released at zhiyiluo.site/misc/clean_v1.0_ sample.json. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09923v1-abstract-full').style.display = 'none'; document.getElementById('2402.09923v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.05561">arXiv:2401.05561</a> <span> [<a href="https://arxiv.org/pdf/2401.05561">pdf</a>, <a href="https://arxiv.org/format/2401.05561">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"> TrustLLM: Trustworthiness in Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yue Huang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+L">Lichao Sun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haoran Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Siyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qihui Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuan Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+C">Chujie Gao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yixin Huang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenhan Lyu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yixuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiner Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhengliang Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yixin Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yijue Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhikun Zhang</a>, <a href="/search/cs?searchtype=author&query=Vidgen%2C+B">Bertie Vidgen</a>, <a href="/search/cs?searchtype=author&query=Kailkhura%2C+B">Bhavya Kailkhura</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+C">Caiming Xiong</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+C">Chaowei Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunyuan Li</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+E">Eric Xing</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+F">Furong Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hao Liu</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+H">Heng Ji</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hongyi Wang</a> , et al. (45 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="2401.05561v6-abstract-short" style="display: inline;"> Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05561v6-abstract-full').style.display = 'inline'; document.getElementById('2401.05561v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05561v6-abstract-full" style="display: none;"> Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05561v6-abstract-full').style.display = 'none'; document.getElementById('2401.05561v6-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 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">This work is still under work and we welcome your contribution</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.08371">arXiv:2312.08371</a> <span> [<a href="https://arxiv.org/pdf/2312.08371">pdf</a>, <a href="https://arxiv.org/format/2312.08371">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"> PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+K">Kuan-Chih Huang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Ming-Hsuan Yang</a>, <a href="/search/cs?searchtype=author&query=Tsai%2C+Y">Yi-Hsuan Tsai</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="2312.08371v2-abstract-short" style="display: inline;"> Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation methods. However, these approaches require per-frame objects or whole point clouds, posing challenges related to memory bank utilization. Moreover, point clouds a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08371v2-abstract-full').style.display = 'inline'; document.getElementById('2312.08371v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.08371v2-abstract-full" style="display: none;"> Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation methods. However, these approaches require per-frame objects or whole point clouds, posing challenges related to memory bank utilization. Moreover, point clouds and trajectory features are combined solely based on concatenation, which may neglect effective interactions between them. In this paper, we propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. To this end, we only utilize point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. Furthermore, we introduce modules to encode trajectory features, focusing on long short-term and future-aware perspectives, and then effectively aggregate them with point cloud features. We conduct extensive experiments on the large-scale Waymo dataset to demonstrate that our approach performs well against state-of-the-art methods. Code and models will be made publicly available at https://github.com/kuanchihhuang/PTT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08371v2-abstract-full').style.display = 'none'; document.getElementById('2312.08371v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 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">Accepted to CVPR 2024. Project page: https://github.com/kuanchihhuang/PTT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.20145">arXiv:2310.20145</a> <span> [<a href="https://arxiv.org/pdf/2310.20145">pdf</a>, <a href="https://arxiv.org/format/2310.20145">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Efficient Robust Bayesian Optimization for Arbitrary Uncertain Inputs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+L">Lin Yang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+J">Junlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhitang 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="2310.20145v2-abstract-short" style="display: inline;"> Bayesian Optimization (BO) is a sample-efficient optimization algorithm widely employed across various applications. In some challenging BO tasks, input uncertainty arises due to the inevitable randomness in the optimization process, such as machining errors, execution noise, or contextual variability. This uncertainty deviates the input from the intended value before evaluation, resulting in sign… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20145v2-abstract-full').style.display = 'inline'; document.getElementById('2310.20145v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.20145v2-abstract-full" style="display: none;"> Bayesian Optimization (BO) is a sample-efficient optimization algorithm widely employed across various applications. In some challenging BO tasks, input uncertainty arises due to the inevitable randomness in the optimization process, such as machining errors, execution noise, or contextual variability. This uncertainty deviates the input from the intended value before evaluation, resulting in significant performance fluctuations in the final result. In this paper, we introduce a novel robust Bayesian Optimization algorithm, AIRBO, which can effectively identify a robust optimum that performs consistently well under arbitrary input uncertainty. Our method directly models the uncertain inputs of arbitrary distributions by empowering the Gaussian Process with the Maximum Mean Discrepancy (MMD) and further accelerates the posterior inference via Nystrom approximation. Rigorous theoretical regret bound is established under MMD estimation error and extensive experiments on synthetic functions and real problems demonstrate that our approach can handle various input uncertainties and achieve state-of-the-art performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20145v2-abstract-full').style.display = 'none'; document.getElementById('2310.20145v2-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 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">Accepted by NeurIPS 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/2310.14480">arXiv:2310.14480</a> <span> [<a href="https://arxiv.org/pdf/2310.14480">pdf</a>, <a href="https://arxiv.org/format/2310.14480">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"> Attention-Enhancing Backdoor Attacks Against BERT-based Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Songzhu Zheng</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+L">Lu Pang</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2310.14480v2-abstract-short" style="display: inline;"> Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. In this paper, we directly target the interior structure of neural… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14480v2-abstract-full').style.display = 'inline'; document.getElementById('2310.14480v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.14480v2-abstract-full" style="display: none;"> Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. In this paper, we directly target the interior structure of neural networks and the backdoor mechanism. We propose a novel Trojan Attention Loss (TAL), which enhances the Trojan behavior by directly manipulating the attention patterns. Our loss can be applied to different attacking methods to boost their attack efficacy in terms of attack successful rates and poisoning rates. It applies to not only traditional dirty-label attacks, but also the more challenging clean-label attacks. We validate our method on different backbone models (BERT, RoBERTa, and DistilBERT) and various tasks (Sentiment Analysis, Toxic Detection, and Topic Classification). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14480v2-abstract-full').style.display = 'none'; document.getElementById('2310.14480v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 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">Findings of EMNLP 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/2309.08681">arXiv:2309.08681</a> <span> [<a href="https://arxiv.org/pdf/2309.08681">pdf</a>, <a href="https://arxiv.org/format/2309.08681">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Near-Field Sensing and Communications with Sparse Arrays: Potentials, Challenges, and Emerging Trends </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2309.08681v1-abstract-short" style="display: inline;"> As a promising technique, extremely large-scale (XL)-arrays offer potential solutions for overcoming the severe path loss in millimeter-wave (mmWave) and TeraHertz (THz) channels, crucial for enabling 6G. Nevertheless, XL-arrays introduce deviations in electromagnetic propagation compared to traditional arrays, fundamentally challenging the assumption with the planar-wave model. Instead, it ushers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08681v1-abstract-full').style.display = 'inline'; document.getElementById('2309.08681v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08681v1-abstract-full" style="display: none;"> As a promising technique, extremely large-scale (XL)-arrays offer potential solutions for overcoming the severe path loss in millimeter-wave (mmWave) and TeraHertz (THz) channels, crucial for enabling 6G. Nevertheless, XL-arrays introduce deviations in electromagnetic propagation compared to traditional arrays, fundamentally challenging the assumption with the planar-wave model. Instead, it ushers in the spherical-wave (SW) model to accurately represent the near-field propagation characteristics, significantly increasing signal processing complexity. Fortunately, the SW model shows remarkable benefits on sensing and communications (S\&C), e.g., improving communication multiplexing capability, spatial resolution, and degrees of freedom. In this context, this article first overviews hardware/algorithm challenges, fundamental potentials, promising applications of near-field S\&C enabled by XL-arrays. To overcome the limitations of existing XL-arrays with dense uniform array layouts and improve S\&C applications, we introduce sparse arrays (SAs). Exploring their potential, we propose XL-SAs for mmWave/THz systems using multi-subarray designs. Finally, several applications, challenges and resarch directions are identified. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08681v1-abstract-full').style.display = 'none'; document.getElementById('2309.08681v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 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/2309.05944">arXiv:2309.05944</a> <span> [<a href="https://arxiv.org/pdf/2309.05944">pdf</a>, <a href="https://arxiv.org/format/2309.05944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Performance Bounds for Near-Field Localization with Widely-Spaced Multi-Subarray mmWave/THz MIMO </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyi Chen</a>, <a href="/search/cs?searchtype=author&query=Xiu%2C+Y">Yue Xiu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2309.05944v1-abstract-short" style="display: inline;"> This paper investigates the potential of near-field localization using widely-spaced multi-subarrays (WSMSs) and analyzing the corresponding angle and range Cram茅r-Rao bounds (CRBs). By employing the Riemann sum, closed-form CRB expressions are derived for the spherical wavefront-based WSMS (SW-WSMS). We find that the CRBs can be characterized by the angular span formed by the line connecting the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.05944v1-abstract-full').style.display = 'inline'; document.getElementById('2309.05944v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.05944v1-abstract-full" style="display: none;"> This paper investigates the potential of near-field localization using widely-spaced multi-subarrays (WSMSs) and analyzing the corresponding angle and range Cram茅r-Rao bounds (CRBs). By employing the Riemann sum, closed-form CRB expressions are derived for the spherical wavefront-based WSMS (SW-WSMS). We find that the CRBs can be characterized by the angular span formed by the line connecting the array's two ends to the target, and the different WSMSs with same angular spans but different number of subarrays have identical normalized CRBs. We provide a theoretical proof that, in certain scenarios, the CRB of WSMSs is smaller than that of uniform arrays. We further yield the closed-form CRBs for the hybrid spherical and planar wavefront-based WSMS (HSPW-WSMS), and its components can be seen as decompositions of the parameters from the CRBs for the SW-WSMS. Simulations are conducted to validate the accuracy of the derived closed-form CRBs and provide further insights into various system characteristics. Basically, this paper underscores the high resolution of utilizing WSMS for localization, reinforces the validity of adopting the HSPW assumption, and, considering its applications in communications, indicates a promising outlook for integrated sensing and communications based on HSPW-WSMSs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.05944v1-abstract-full').style.display = 'none'; document.getElementById('2309.05944v1-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 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/2308.04660">arXiv:2308.04660</a> <span> [<a href="https://arxiv.org/pdf/2308.04660">pdf</a>, <a href="https://arxiv.org/format/2308.04660">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"> Efficient Bayesian Optimization with Deep Kernel Learning and Transformer Pre-trained on Multiple Heterogeneous Datasets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Shoubo Hu</a>, <a href="/search/cs?searchtype=author&query=Chuai%2C+J">Jie Chuai</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhitang 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="2308.04660v1-abstract-short" style="display: inline;"> Bayesian optimization (BO) is widely adopted in black-box optimization problems and it relies on a surrogate model to approximate the black-box response function. With the increasing number of black-box optimization tasks solved and even more to solve, the ability to learn from multiple prior tasks to jointly pre-train a surrogate model is long-awaited to further boost optimization efficiency. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04660v1-abstract-full').style.display = 'inline'; document.getElementById('2308.04660v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.04660v1-abstract-full" style="display: none;"> Bayesian optimization (BO) is widely adopted in black-box optimization problems and it relies on a surrogate model to approximate the black-box response function. With the increasing number of black-box optimization tasks solved and even more to solve, the ability to learn from multiple prior tasks to jointly pre-train a surrogate model is long-awaited to further boost optimization efficiency. In this paper, we propose a simple approach to pre-train a surrogate, which is a Gaussian process (GP) with a kernel defined on deep features learned from a Transformer-based encoder, using datasets from prior tasks with possibly heterogeneous input spaces. In addition, we provide a simple yet effective mix-up initialization strategy for input tokens corresponding to unseen input variables and therefore accelerate new tasks' convergence. Experiments on both synthetic and real benchmark problems demonstrate the effectiveness of our proposed pre-training and transfer BO strategy over existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04660v1-abstract-full').style.display = 'none'; document.getElementById('2308.04660v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.01430">arXiv:2307.01430</a> <span> [<a href="https://arxiv.org/pdf/2307.01430">pdf</a>, <a href="https://arxiv.org/format/2307.01430">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"> Continual Learning in Open-vocabulary Classification with Complementary Memory Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhen Zhu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yao Xiao</a>, <a href="/search/cs?searchtype=author&query=Hoiem%2C+D">Derek Hoiem</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="2307.01430v3-abstract-short" style="display: inline;"> We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. Specifically, we propose to combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within the exemplar classes.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.01430v3-abstract-full').style.display = 'inline'; document.getElementById('2307.01430v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.01430v3-abstract-full" style="display: none;"> We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. Specifically, we propose to combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within the exemplar classes. We also propose a "tree probe" method, an adaption of lazy learning principles, which enables fast learning from new examples with competitive accuracy to batch-trained linear models. We test in data incremental, class incremental, and task incremental settings, as well as ability to perform flexible inference on varying subsets of zero-shot and learned categories. Our proposed method achieves a good balance of learning speed, target task effectiveness, and zero-shot effectiveness. Code will be available at https://github.com/jessemelpolio/TreeProbe. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.01430v3-abstract-full').style.display = 'none'; document.getElementById('2307.01430v3-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">Accepted by Transactions on Machine Learning Research (TMLR)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.01425">arXiv:2307.01425</a> <span> [<a href="https://arxiv.org/pdf/2307.01425">pdf</a>, <a href="https://arxiv.org/format/2307.01425">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"> Consistent Multimodal Generation via A Unified GAN Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhen Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yijun Li</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+K+K">Krishna Kumar Singh</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+Z">Zhixin Shu</a>, <a href="/search/cs?searchtype=author&query=Pirk%2C+S">Soeren Pirk</a>, <a href="/search/cs?searchtype=author&query=Hoiem%2C+D">Derek Hoiem</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="2307.01425v1-abstract-short" style="display: inline;"> We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the StyleGAN3 architecture, with a shared backbone and modality-specific branches in the last layers of the synthesis network, and we propose per-modality… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.01425v1-abstract-full').style.display = 'inline'; document.getElementById('2307.01425v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.01425v1-abstract-full" style="display: none;"> We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the StyleGAN3 architecture, with a shared backbone and modality-specific branches in the last layers of the synthesis network, and we propose per-modality fidelity discriminators and a cross-modality consistency discriminator. In experiments on the Stanford2D3D dataset, we demonstrate realistic and consistent generation of RGB, depth, and normal images. We also show a training recipe to easily extend our pretrained model on a new domain, even with a few pairwise data. We further evaluate the use of synthetically generated RGB and depth pairs for training or fine-tuning depth estimators. Code will be available at https://github.com/jessemelpolio/MultimodalGAN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.01425v1-abstract-full').style.display = 'none'; document.getElementById('2307.01425v1-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">In review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.05704">arXiv:2306.05704</a> <span> [<a href="https://arxiv.org/pdf/2306.05704">pdf</a>, <a href="https://arxiv.org/format/2306.05704">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="Multimedia">cs.MM</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"> Exploring Effective Mask Sampling Modeling for Neural Image Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lin Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+M">Mingming Zhao</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shanxin Yuan</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wengang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Houqiang Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanfeng Wang</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Q">Qi Tian</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="2306.05704v1-abstract-short" style="display: inline;"> Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel redundancy. Inspired by the mask sampling modeling in recent self-supervised learning methods for natural language processing and high-level vision, we propose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.05704v1-abstract-full').style.display = 'inline'; document.getElementById('2306.05704v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.05704v1-abstract-full" style="display: none;"> Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel redundancy. Inspired by the mask sampling modeling in recent self-supervised learning methods for natural language processing and high-level vision, we propose a novel pretraining strategy for neural image compression. Specifically, Cube Mask Sampling Module (CMSM) is proposed to apply both spatial and channel mask sampling modeling to image compression in the pre-training stage. Moreover, to further reduce channel redundancy, we propose the Learnable Channel Mask Module (LCMM) and the Learnable Channel Completion Module (LCCM). Our plug-and-play CMSM, LCMM, LCCM modules can apply to both CNN-based and Transformer-based architectures, significantly reduce the computational cost, and improve the quality of images. Experiments on the public Kodak and Tecnick datasets demonstrate that our method achieves competitive performance with lower computational complexity compared to state-of-the-art image compression methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.05704v1-abstract-full').style.display = 'none'; document.getElementById('2306.05704v1-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.05722">arXiv:2305.05722</a> <span> [<a href="https://arxiv.org/pdf/2305.05722">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="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Clinical Predictive Modeling through Model Complexity-Driven Class Proportion Tuning for Class Imbalanced Data: An Empirical Study on Opioid Overdose Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yinan Liu</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+X">Xinyu Dong</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Rosenthal%2C+R+N">Richard N. Rosenthal</a>, <a href="/search/cs?searchtype=author&query=Wong%2C+R">Rachel Wong</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tengfei Ma</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fusheng 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="2305.05722v1-abstract-short" style="display: inline;"> Class imbalance problems widely exist in the medical field and heavily deteriorates performance of clinical predictive models. Most techniques to alleviate the problem rebalance class proportions and they predominantly assume the rebalanced proportions should be a function of the original data and oblivious to the model one uses. This work challenges this prevailing assumption and proposes that li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.05722v1-abstract-full').style.display = 'inline'; document.getElementById('2305.05722v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.05722v1-abstract-full" style="display: none;"> Class imbalance problems widely exist in the medical field and heavily deteriorates performance of clinical predictive models. Most techniques to alleviate the problem rebalance class proportions and they predominantly assume the rebalanced proportions should be a function of the original data and oblivious to the model one uses. This work challenges this prevailing assumption and proposes that links the optimal class proportions to the model complexity, thereby tuning the class proportions per model. Our experiments on the opioid overdose prediction problem highlight the performance gain of tuning class proportions. Rigorous regression analysis also confirms the advantages of the theoretical framework proposed and the statistically significant correlation between the hyperparameters controlling the model complexity and the optimal class proportions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.05722v1-abstract-full').style.display = 'none'; document.getElementById('2305.05722v1-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 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/2305.04436">arXiv:2305.04436</a> <span> [<a href="https://arxiv.org/pdf/2305.04436">pdf</a>, <a href="https://arxiv.org/format/2305.04436">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"> Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yin%2C+Z">Zhaoxia Yin</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shaowei Zhu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+H">Hang Su</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Jianteng Peng</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanli Lyu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+B">Bin Luo</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="2305.04436v1-abstract-short" style="display: inline;"> Deep Neural Networks (DNNs) have recently made significant progress in many fields. However, studies have shown that DNNs are vulnerable to adversarial examples, where imperceptible perturbations can greatly mislead DNNs even if the full underlying model parameters are not accessible. Various defense methods have been proposed, such as feature compression and gradient masking. However, numerous st… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.04436v1-abstract-full').style.display = 'inline'; document.getElementById('2305.04436v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.04436v1-abstract-full" style="display: none;"> Deep Neural Networks (DNNs) have recently made significant progress in many fields. However, studies have shown that DNNs are vulnerable to adversarial examples, where imperceptible perturbations can greatly mislead DNNs even if the full underlying model parameters are not accessible. Various defense methods have been proposed, such as feature compression and gradient masking. However, numerous studies have proven that previous methods create detection or defense against certain attacks, which renders the method ineffective in the face of the latest unknown attack methods. The invisibility of adversarial perturbations is one of the evaluation indicators for adversarial example attacks, which also means that the difference in the local correlation of high-frequency information in adversarial examples and normal examples can be used as an effective feature to distinguish the two. Therefore, we propose an adversarial example detection framework based on a high-frequency information enhancement strategy, which can effectively extract and amplify the feature differences between adversarial examples and normal examples. Experimental results show that the feature augmentation module can be combined with existing detection models in a modular way under this framework. Improve the detector's performance and reduce the deployment cost without modifying the existing detection model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.04436v1-abstract-full').style.display = 'none'; document.getElementById('2305.04436v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 May, 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/2304.00440">arXiv:2304.00440</a> <span> [<a href="https://arxiv.org/pdf/2304.00440">pdf</a>, <a href="https://arxiv.org/format/2304.00440">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Near-Field Channel Estimation for Extremely Large-Scale Reconfigurable Intelligent Surface (XL-RIS)-Aided Wideband mmWave Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+C">Chenfei Xie</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+B">Boyu Ning</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2304.00440v1-abstract-short" style="display: inline;"> Near-field communications present new opportunities over near-field channels, however, the spherical wavefront propagation makes near-field signal processing challenging. In this context, this paper proposes efficient near-field channel estimation methods for wideband MIMO mmWave systems with the aid of extremely large-scale reconfigurable intelligent surfaces (XL-RIS). For the wideband signals re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00440v1-abstract-full').style.display = 'inline'; document.getElementById('2304.00440v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.00440v1-abstract-full" style="display: none;"> Near-field communications present new opportunities over near-field channels, however, the spherical wavefront propagation makes near-field signal processing challenging. In this context, this paper proposes efficient near-field channel estimation methods for wideband MIMO mmWave systems with the aid of extremely large-scale reconfigurable intelligent surfaces (XL-RIS). For the wideband signals reflected by the analog RIS, we characterize their near-field beam squint effect in both angle and distance domains. Based on the mathematical analysis of the near-field beam patterns over all frequencies, a wideband spherical-domain dictionary is constructed by minimizing the coherence of two arbitrary beams. In light of this, we formulate a two-dimensional compressive sensing problem to recover the channel parameter based on the spherical-domain sparsity of mmWave channels. To this end, we present a correlation coefficient-based atom matching method within our proposed multi-frequency parallelizable subspace recovery framework for efficient solutions. Additionally, we propose a two-dimensional oracle estimator as a benchmark and derive its lower bound across all subcarriers. Our findings emphasize the significance of system hyperparameters and the sensing matrix of each subcarrier in determining the accuracy of the estimation. Finally, numerical results show that our proposed method achieves considerable performance compared with the lower bound and has a time complexity linear to the number of RIS elements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00440v1-abstract-full').style.display = 'none'; document.getElementById('2304.00440v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.14400">arXiv:2303.14400</a> <span> [<a href="https://arxiv.org/pdf/2303.14400">pdf</a>, <a href="https://arxiv.org/format/2303.14400">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Reconfigurable Intelligent Surface-Aided Full-Duplex mmWave MIMO: Channel Estimation, Passive and Hybrid Beamforming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Xanthos%2C+Y">Yunis Xanthos</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Assi%2C+C">Chadi Assi</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2303.14400v1-abstract-short" style="display: inline;"> Millimeter wave (mmWave) full-duplex (FD) is a promising technique for improving capacity by maximizing the utilization of both time and the rich mmWave frequency resources. Still, it has restrictions due to FD self-interference (SI) and mmWave's limited coverage. Therefore, this study dives into FD mmWave MIMO with the assistance of reconfigurable intelligent surfaces (RIS) for capacity improveme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.14400v1-abstract-full').style.display = 'inline'; document.getElementById('2303.14400v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.14400v1-abstract-full" style="display: none;"> Millimeter wave (mmWave) full-duplex (FD) is a promising technique for improving capacity by maximizing the utilization of both time and the rich mmWave frequency resources. Still, it has restrictions due to FD self-interference (SI) and mmWave's limited coverage. Therefore, this study dives into FD mmWave MIMO with the assistance of reconfigurable intelligent surfaces (RIS) for capacity improvement. First, we demonstrate the angular-domain reciprocity of FD antenna arrays under the far-field planar wavefront assumption. Accordingly, a strategy for joint downlink-uplink (DL-UL) channel estimation is presented. For estimating the SI channel, the direct channel, and the cascaded channel, the Khatri-Rao product-based compressive sensing (KR-CS), distributed CS (D-CS), and two-stage multiple measurement vector-based D-CS (M-D-CS) frameworks are proposed, respectively. Additionally, we propose a passive beamforming optimization solution based on the angular-domain cascaded channel. With hybrid beamforming architectures, a novel hybrid weighted minimum mean squared error method for SI cancellation (H-WMMSE-SIC) is proposed. Simulations have revealed that joint DL-UL processing significantly improves estimation performance in comparison to separate DL/UL channel estimation. Particularly, when the interference-to-noise ratio is less than 35 dB, our proposed H-WMMSE-SIC offers spectral efficiency performance comparable to fully-digital WMMSE-SIC. Finally, the computational complexity is analyzed for our proposed methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.14400v1-abstract-full').style.display = 'none'; document.getElementById('2303.14400v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 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/2302.09501">arXiv:2302.09501</a> <span> [<a href="https://arxiv.org/pdf/2302.09501">pdf</a>, <a href="https://arxiv.org/format/2302.09501">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Meta Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xiuzhen Cheng</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Minghui Xu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+R">Runyu Pan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Dongxiao Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chenxu Wang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xue Xiao</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weifeng Lyu</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="2302.09501v1-abstract-short" style="display: inline;"> With the continuous improvement of information infrastructures, academia and industry have been constantly exploring new computing paradigms to fully exploit computing powers. In this paper, we propose Meta Computing, a new computing paradigm that aims to utilize all available computing resources hooked on the Internet, provide efficient, fault-tolerant, and personalized services with strong secur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.09501v1-abstract-full').style.display = 'inline'; document.getElementById('2302.09501v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.09501v1-abstract-full" style="display: none;"> With the continuous improvement of information infrastructures, academia and industry have been constantly exploring new computing paradigms to fully exploit computing powers. In this paper, we propose Meta Computing, a new computing paradigm that aims to utilize all available computing resources hooked on the Internet, provide efficient, fault-tolerant, and personalized services with strong security and privacy guarantee, and virtualize the Internet as a giant computer, that is, ``Network-as-a-Computer, NaaC'', or ``Meta Computer'' for short, for any task or any person on-demand. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.09501v1-abstract-full').style.display = 'none'; document.getElementById('2302.09501v1-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 papes, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.12640">arXiv:2301.12640</a> <span> [<a href="https://arxiv.org/pdf/2301.12640">pdf</a>, <a href="https://arxiv.org/format/2301.12640">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="Analysis of PDEs">math.AP</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"> Reweighted Interacting Langevin Diffusions: an Accelerated Sampling Methodfor Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+J">Junlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhitang Chen</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+J">Jianye Hao</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="2301.12640v1-abstract-short" style="display: inline;"> We proposed a new technique to accelerate sampling methods for solving difficult optimization problems. Our method investigates the intrinsic connection between posterior distribution sampling and optimization with Langevin dynamics, and then we propose an interacting particle scheme that approximates a Reweighted Interacting Langevin Diffusion system (RILD). The underlying system is designed by a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.12640v1-abstract-full').style.display = 'inline'; document.getElementById('2301.12640v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.12640v1-abstract-full" style="display: none;"> We proposed a new technique to accelerate sampling methods for solving difficult optimization problems. Our method investigates the intrinsic connection between posterior distribution sampling and optimization with Langevin dynamics, and then we propose an interacting particle scheme that approximates a Reweighted Interacting Langevin Diffusion system (RILD). The underlying system is designed by adding a multiplicative source term into the classical Langevin operator, leading to a higher convergence rate and a more concentrated invariant measure. We analyze the convergence rate of our algorithm and the improvement compared to existing results in the asymptotic situation. We also design various tests to verify our theoretical results, showing the advantages of accelerating convergence and breaking through barriers of suspicious local minimums, especially in high-dimensional non-convex settings. Our algorithms and analysis shed some light on combining gradient and genetic algorithms using Partial Differential Equations (PDEs) with provable guarantees. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.12640v1-abstract-full').style.display = 'none'; document.getElementById('2301.12640v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.01369">arXiv:2301.01369</a> <span> [<a href="https://arxiv.org/pdf/2301.01369">pdf</a>, <a href="https://arxiv.org/format/2301.01369">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <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"> Brain Tissue Segmentation Across the Human Lifespan via Supervised Contrastive Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiaoyang Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jinjian Wu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenjiao Lyu</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yicheng Zou</a>, <a href="/search/cs?searchtype=author&query=Thung%2C+K">Kim-Han Thung</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Siyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ye Wu</a>, <a href="/search/cs?searchtype=author&query=Ahmad%2C+S">Sahar Ahmad</a>, <a href="/search/cs?searchtype=author&query=Yap%2C+P">Pew-Thian Yap</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="2301.01369v1-abstract-short" style="display: inline;"> Automatic segmentation of brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is critical for tissue volumetric analysis and cortical surface reconstruction. Due to dramatic structural and appearance changes associated with developmental and aging processes, existing brain tissue segmentation methods are only viable for specific age groups. Consequently, methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01369v1-abstract-full').style.display = 'inline'; document.getElementById('2301.01369v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.01369v1-abstract-full" style="display: none;"> Automatic segmentation of brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is critical for tissue volumetric analysis and cortical surface reconstruction. Due to dramatic structural and appearance changes associated with developmental and aging processes, existing brain tissue segmentation methods are only viable for specific age groups. Consequently, methods developed for one age group may fail for another. In this paper, we make the first attempt to segment brain tissues across the entire human lifespan (0-100 years of age) using a unified deep learning model. To overcome the challenges related to structural variability underpinned by biological processes, intensity inhomogeneity, motion artifacts, scanner-induced differences, and acquisition protocols, we propose to use contrastive learning to improve the quality of feature representations in a latent space for effective lifespan tissue segmentation. We compared our approach with commonly used segmentation methods on a large-scale dataset of 2,464 MR images. Experimental results show that our model accurately segments brain tissues across the lifespan and outperforms existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01369v1-abstract-full').style.display = 'none'; document.getElementById('2301.01369v1-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.08341">arXiv:2212.08341</a> <span> [<a href="https://arxiv.org/pdf/2212.08341">pdf</a>, <a href="https://arxiv.org/ps/2212.08341">ps</a>, <a href="https://arxiv.org/format/2212.08341">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div 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/10.1007/978-981-99-0856-1_30">10.1007/978-981-99-0856-1_30 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adversarial Example Defense via Perturbation Grading Strategy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shaowei Zhu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanli Lyu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bin Li</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+Z">Zhaoxia Yin</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+B">Bin Luo</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="2212.08341v1-abstract-short" style="display: inline;"> Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researcher… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.08341v1-abstract-full').style.display = 'inline'; document.getElementById('2212.08341v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.08341v1-abstract-full" style="display: none;"> Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.08341v1-abstract-full').style.display = 'none'; document.getElementById('2212.08341v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IFTC 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.16183">arXiv:2211.16183</a> <span> [<a href="https://arxiv.org/pdf/2211.16183">pdf</a>, <a href="https://arxiv.org/format/2211.16183">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Active 3D Double-RIS-Aided Multi-User Communications: Two-Timescale-Based Separate Channel Estimation via Bayesian Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songjie Yang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wanting Lyu</a>, <a href="/search/cs?searchtype=author&query=Xiu%2C+Y">Yue Xiu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongpei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2211.16183v1-abstract-short" style="display: inline;"> Double-reconfigurable intelligent surface (RIS) is a promising technique, achieving a substantial gain improvement compared to single-RIS techniques. However, in double-RIS-aided systems, accurate channel estimation is more challenging than in single-RIS-aided systems. This work solves the problem of double-RIS-based channel estimation based on active RIS architectures with only one radio frequenc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.16183v1-abstract-full').style.display = 'inline'; document.getElementById('2211.16183v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.16183v1-abstract-full" style="display: none;"> Double-reconfigurable intelligent surface (RIS) is a promising technique, achieving a substantial gain improvement compared to single-RIS techniques. However, in double-RIS-aided systems, accurate channel estimation is more challenging than in single-RIS-aided systems. This work solves the problem of double-RIS-based channel estimation based on active RIS architectures with only one radio frequency (RF) chain. Since the slow time-varying channels, i.e., the BS-RIS 1, BS-RIS 2, and RIS 1-RIS 2 channels, can be obtained with active RIS architectures, a novel multi-user two-timescale channel estimation protocol is proposed to minimize the pilot overhead. First, we propose an uplink training scheme for slow time-varying channel estimation, which can effectively address the double-reflection channel estimation problem. With channels' sparisty, a low-complexity Singular Value Decomposition Multiple Measurement Vector-Based Compressive Sensing (SVD-MMV-CS) framework with the line-of-sight (LoS)-aided off-grid MMV expectation maximization-based generalized approximate message passing (M-EM-GAMP) algorithm is proposed for channel parameter recovery. For fast time-varying channel estimation, based on the estimated large-timescale channels, a measurements-augmentation-estimate (MAE) framework is developed to decrease the pilot overhead.Additionally, a comprehensive analysis of pilot overhead and computing complexity is conducted. Finally, the simulation results demonstrate the effectiveness of our proposed multi-user two-timescale estimation strategy and the low-complexity Bayesian CS framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.16183v1-abstract-full').style.display = 'none'; document.getElementById('2211.16183v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.10240">arXiv:2208.10240</a> <span> [<a href="https://arxiv.org/pdf/2208.10240">pdf</a>, <a href="https://arxiv.org/format/2208.10240">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+X">Xinyu Dong</a>, <a href="/search/cs?searchtype=author&query=Wong%2C+R">Rachel Wong</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Songzhu Zheng</a>, <a href="/search/cs?searchtype=author&query=Abell-Hart%2C+K">Kayley Abell-Hart</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fusheng Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2208.10240v2-abstract-short" style="display: inline;"> Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases. Meanwhile, large amounts of narrative clinical notes provide complementary information, but are often not integrated into predictive models. In this paper, we provide a novel multimodal transformer to fuse clinical notes and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10240v2-abstract-full').style.display = 'inline'; document.getElementById('2208.10240v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.10240v2-abstract-full" style="display: none;"> Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases. Meanwhile, large amounts of narrative clinical notes provide complementary information, but are often not integrated into predictive models. In this paper, we provide a novel multimodal transformer to fuse clinical notes and structured EHR data for better prediction of in-hospital mortality. To improve interpretability, we propose an integrated gradients (IG) method to select important words in clinical notes and discover the critical structured EHR features with Shapley values. These important words and clinical features are visualized to assist with interpretation of the prediction outcomes. We also investigate the significance of domain adaptive pretraining and task adaptive fine-tuning on the Clinical BERT, which is used to learn the representations of clinical notes. Experiments demonstrated that our model outperforms other methods (AUCPR: 0.538, AUCROC: 0.877, F1:0.490). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10240v2-abstract-full').style.display = 'none'; document.getElementById('2208.10240v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </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">AMIA Annual Symposium Proceedings 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> AMIA Annu Symp Proc 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.04946">arXiv:2208.04946</a> <span> [<a href="https://arxiv.org/pdf/2208.04946">pdf</a>, <a href="https://arxiv.org/format/2208.04946">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Attention Hijacking in Trojan Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Songzhu Zheng</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tengfei Ma</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2208.04946v1-abstract-short" style="display: inline;"> Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a central question: Can we reveal the Trojans through attention mechanisms in BERTs and ViTs? In this paper, we investigate the attention hijacking pattern in Trojan AIs, \ie, the trigger token ``kidnaps'' the attention weight… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04946v1-abstract-full').style.display = 'inline'; document.getElementById('2208.04946v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.04946v1-abstract-full" style="display: none;"> Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a central question: Can we reveal the Trojans through attention mechanisms in BERTs and ViTs? In this paper, we investigate the attention hijacking pattern in Trojan AIs, \ie, the trigger token ``kidnaps'' the attention weights when a specific trigger is present. We observe the consistent attention hijacking pattern in Trojan Transformers from both Natural Language Processing (NLP) and Computer Vision (CV) domains. This intriguing property helps us to understand the Trojan mechanism in BERTs and ViTs. We also propose an Attention-Hijacking Trojan Detector (AHTD) to discriminate the Trojan AIs from the clean ones. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04946v1-abstract-full').style.display = 'none'; document.getElementById('2208.04946v1-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.09682">arXiv:2206.09682</a> <span> [<a href="https://arxiv.org/pdf/2206.09682">pdf</a>, <a href="https://arxiv.org/format/2206.09682">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chejian Xu</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+W">Wenhao Ding</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zuxin Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuai Wang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yihan He</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Hanjiang Hu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+D">Ding Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bo Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.09682v4-abstract-short" style="display: inline;"> As shown by recent studies, machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts. This has raised great concerns about deploying machine learning algorithms for real-world applications, especially in safety-critical domains such as autonomous driving (AD). On the other hand, traditional AD testing on natural… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.09682v4-abstract-full').style.display = 'inline'; document.getElementById('2206.09682v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.09682v4-abstract-full" style="display: none;"> As shown by recent studies, machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts. This has raised great concerns about deploying machine learning algorithms for real-world applications, especially in safety-critical domains such as autonomous driving (AD). On the other hand, traditional AD testing on naturalistic scenarios requires hundreds of millions of driving miles due to the high dimensionality and rareness of the safety-critical scenarios in the real world. As a result, several approaches for autonomous driving evaluation have been explored, which are usually, however, based on different simulation platforms, types of safety-critical scenarios, scenario generation algorithms, and driving route variations. Thus, despite a large amount of effort in autonomous driving testing, it is still challenging to compare and understand the effectiveness and efficiency of different testing scenario generation algorithms and testing mechanisms under similar conditions. In this paper, we aim to provide the first unified platform SafeBench to integrate different types of safety-critical testing scenarios, scenario generation algorithms, and other variations such as driving routes and environments. Meanwhile, we implement 4 deep reinforcement learning-based AD algorithms with 4 types of input (e.g., bird's-eye view, camera) to perform fair comparisons on SafeBench. We find our generated testing scenarios are indeed more challenging and observe the trade-off between the performance of AD agents under benign and safety-critical testing scenarios. We believe our unified platform SafeBench for large-scale and effective autonomous driving testing will motivate the development of new testing scenario generation and safe AD algorithms. SafeBench is available at https://safebench.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.09682v4-abstract-full').style.display = 'none'; document.getElementById('2206.09682v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </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">Published as a conference paper at NeurIPS 2022 (Track on Datasets and Benchmarks)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.08305">arXiv:2205.08305</a> <span> [<a href="https://arxiv.org/pdf/2205.08305">pdf</a>, <a href="https://arxiv.org/format/2205.08305">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A Study of the Attention Abnormality in Trojaned BERTs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Songzhu Zheng</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tengfei Ma</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao 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="2205.08305v2-abstract-short" style="display: inline;"> Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of Trojaned models, i.e., when encountering an poisoned input, the trigger token hijacks the attention focus regardless of the context. We provide a thorough qualitative and quantitative analysis of this phenomenon, reveali… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.08305v2-abstract-full').style.display = 'inline'; document.getElementById('2205.08305v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.08305v2-abstract-full" style="display: none;"> Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of Trojaned models, i.e., when encountering an poisoned input, the trigger token hijacks the attention focus regardless of the context. We provide a thorough qualitative and quantitative analysis of this phenomenon, revealing insights into the Trojan mechanism. Based on the observation, we propose an attention-based Trojan detector to distinguish Trojaned models from clean ones. To the best of our knowledge, this is the first paper to analyze the Trojan mechanism and to develop a Trojan detector based on the transformer's attention. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.08305v2-abstract-full').style.display = 'none'; document.getElementById('2205.08305v2-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </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">NAACL-HLT 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.12456">arXiv:2202.12456</a> <span> [<a href="https://arxiv.org/pdf/2202.12456">pdf</a>, <a href="https://arxiv.org/format/2202.12456">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> <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/10.1109/TAFFC.2022.3154332">10.1109/TAFFC.2022.3154332 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Prediction of Depression Severity Based on the Prosodic and Semantic Features with Bidirectional LSTM and Time Distributed CNN </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mao%2C+K">Kaining Mao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D+B">Deborah Baofeng Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+A">Ang Li</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+R">Rongqi Jiao</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yanhui Zhu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+B">Bin Wu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+T">Tiansheng Zheng</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+L">Lei Qian</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wei Lyu</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+M">Minjie Ye</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jie 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="2202.12456v1-abstract-short" style="display: inline;"> Depression is increasingly impacting individuals both physically and psychologically worldwide. It has become a global major public health problem and attracts attention from various research fields. Traditionally, the diagnosis of depression is formulated through semi-structured interviews and supplementary questionnaires, which makes the diagnosis heavily relying on physicians experience and is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12456v1-abstract-full').style.display = 'inline'; document.getElementById('2202.12456v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.12456v1-abstract-full" style="display: none;"> Depression is increasingly impacting individuals both physically and psychologically worldwide. It has become a global major public health problem and attracts attention from various research fields. Traditionally, the diagnosis of depression is formulated through semi-structured interviews and supplementary questionnaires, which makes the diagnosis heavily relying on physicians experience and is subject to bias. Mental health monitoring and cloud-based remote diagnosis can be implemented through an automated depression diagnosis system. In this article, we propose an attention-based multimodality speech and text representation for depression prediction. Our model is trained to estimate the depression severity of participants using the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) dataset. For the audio modality, we use the collaborative voice analysis repository (COVAREP) features provided by the dataset and employ a Bidirectional Long Short-Term Memory Network (Bi-LSTM) followed by a Time-distributed Convolutional Neural Network (T-CNN). For the text modality, we use global vectors for word representation (GloVe) to perform word embeddings and the embeddings are fed into the Bi-LSTM network. Results show that both audio and text models perform well on the depression severity estimation task, with best sequence level F1 score of 0.9870 and patient-level F1 score of 0.9074 for the audio model over five classes (healthy, mild, moderate, moderately severe, and severe), as well as sequence level F1 score of 0.9709 and patient-level F1 score of 0.9245 for the text model over five classes. Results are similar for the multimodality fused model, with the highest F1 score of 0.9580 on the patient-level depression detection task over five classes. Experiments show statistically significant improvements over previous works. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12456v1-abstract-full').style.display = 'none'; document.getElementById('2202.12456v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 7 figures, already accepted by IEEE Transactions on Affective Computing, listed in early access now</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.03609">arXiv:2106.03609</a> <span> [<a href="https://arxiv.org/pdf/2106.03609">pdf</a>, <a href="https://arxiv.org/format/2106.03609">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"> High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Grosnit%2C+A">Antoine Grosnit</a>, <a href="/search/cs?searchtype=author&query=Tutunov%2C+R">Rasul Tutunov</a>, <a href="/search/cs?searchtype=author&query=Maraval%2C+A+M">Alexandre Max Maraval</a>, <a href="/search/cs?searchtype=author&query=Griffiths%2C+R">Ryan-Rhys Griffiths</a>, <a href="/search/cs?searchtype=author&query=Cowen-Rivers%2C+A+I">Alexander I. Cowen-Rivers</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Lin Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Lin Zhu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhitang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/cs?searchtype=author&query=Peters%2C+J">Jan Peters</a>, <a href="/search/cs?searchtype=author&query=Bou-Ammar%2C+H">Haitham Bou-Ammar</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="2106.03609v3-abstract-short" style="display: inline;"> We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By adapting ideas from deep metric learning, we use label guidance from the blackbox function to structure the VAE latent space, facilitating the Gaussian process fit and yielding improved BO performance. Importantly for B… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.03609v3-abstract-full').style.display = 'inline'; document.getElementById('2106.03609v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.03609v3-abstract-full" style="display: none;"> We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By adapting ideas from deep metric learning, we use label guidance from the blackbox function to structure the VAE latent space, facilitating the Gaussian process fit and yielding improved BO performance. Importantly for BO problem settings, our method operates in semi-supervised regimes where only few labelled data points are available. We run experiments on three real-world tasks, achieving state-of-the-art results on the penalised logP molecule generation benchmark using just 3% of the labelled data required by previous approaches. As a theoretical contribution, we present a proof of vanishing regret for VAE BO. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.03609v3-abstract-full').style.display = 'none'; document.getElementById('2106.03609v3-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 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.03826">arXiv:2012.03826</a> <span> [<a href="https://arxiv.org/pdf/2012.03826">pdf</a>, <a href="https://arxiv.org/format/2012.03826">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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cowen-Rivers%2C+A+I">Alexander I. Cowen-Rivers</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Tutunov%2C+R">Rasul Tutunov</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhi Wang</a>, <a href="/search/cs?searchtype=author&query=Grosnit%2C+A">Antoine Grosnit</a>, <a href="/search/cs?searchtype=author&query=Griffiths%2C+R+R">Ryan Rhys Griffiths</a>, <a href="/search/cs?searchtype=author&query=Maraval%2C+A+M">Alexandre Max Maraval</a>, <a href="/search/cs?searchtype=author&query=Jianye%2C+H">Hao Jianye</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/cs?searchtype=author&query=Peters%2C+J">Jan Peters</a>, <a href="/search/cs?searchtype=author&query=Ammar%2C+H+B">Haitham Bou Ammar</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="2012.03826v6-abstract-short" style="display: inline;"> In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.03826v6-abstract-full').style.display = 'inline'; document.getElementById('2012.03826v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.03826v6-abstract-full" style="display: none;"> In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO's empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto front solutions improve queried configurations, and robust acquisition maximisers afford empirical advantages relative to their non-robust counterparts. We hope these findings may serve as guiding principles for practitioners of Bayesian optimisation. All code is made available at https://github.com/huawei-noah/HEBO. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.03826v6-abstract-full').style.display = 'none'; document.getElementById('2012.03826v6-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at JAIR</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.04987">arXiv:2011.04987</a> <span> [<a href="https://arxiv.org/pdf/2011.04987">pdf</a>, <a href="https://arxiv.org/format/2011.04987">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> CircuitBot: Learning to Survive with Robotic Circuit Drawing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tan%2C+X">Xianglong Tan</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weijie Lyu</a>, <a href="/search/cs?searchtype=author&query=Rosendo%2C+A">Andre Rosendo</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="2011.04987v2-abstract-short" style="display: inline;"> Robots with the ability to actively acquire power from surroundings will be greatly beneficial for long-term autonomy, and to survive in dynamic, uncertain environments. In this work, a scenario is presented where a robot has limited energy, and the only way to survive is to access the energy from a power source. With no cables or wires available, the robot learns to construct an electrical path a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04987v2-abstract-full').style.display = 'inline'; document.getElementById('2011.04987v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.04987v2-abstract-full" style="display: none;"> Robots with the ability to actively acquire power from surroundings will be greatly beneficial for long-term autonomy, and to survive in dynamic, uncertain environments. In this work, a scenario is presented where a robot has limited energy, and the only way to survive is to access the energy from a power source. With no cables or wires available, the robot learns to construct an electrical path and avoid potential obstacles during the connection. We present this robot, capable of drawing connected circuit patterns with graphene-based conductive ink. A state-of-the-art Mix-Variable Bayesian Optimization is adopted to optimize the placement of conductive shapes to maximize the power this robot receives. Our results show that, within a small number of trials, the robot learns to build parallel circuits to maximize the voltage received and avoid obstacles which steal energy from the robot. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04987v2-abstract-full').style.display = 'none'; document.getElementById('2011.04987v2-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 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.03220">arXiv:2007.03220</a> <span> [<a href="https://arxiv.org/pdf/2007.03220">pdf</a>, <a href="https://arxiv.org/format/2007.03220">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Sapphire: Automatic Configuration Recommendation for Distributed Storage Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenhao Lyu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Youyou Lu</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+J">Jiwu Shu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wei Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2007.03220v1-abstract-short" style="display: inline;"> Modern distributed storage systems come with aplethora of configurable parameters that controlmodule behavior and affect system performance. Default settings provided by developers are often suboptimal for specific user cases. Tuning parameters can provide significant performance gains but is a difficult task requiring profound experience and expertise, due to the immense number of configurable pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.03220v1-abstract-full').style.display = 'inline'; document.getElementById('2007.03220v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.03220v1-abstract-full" style="display: none;"> Modern distributed storage systems come with aplethora of configurable parameters that controlmodule behavior and affect system performance. Default settings provided by developers are often suboptimal for specific user cases. Tuning parameters can provide significant performance gains but is a difficult task requiring profound experience and expertise, due to the immense number of configurable parameters, complex inner dependencies and non-linearsystem behaviors. To overcome these difficulties, we propose an automatic simulation-based approach, Sapphire, to recommend optimal configurations by leveraging machine learning and black-box optimization techniques. We evaluate Sapphire on Ceph. Results show that Sapphire significantly boosts Ceph performance to 2.2x compared to the default configuration. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.03220v1-abstract-full').style.display = 'none'; document.getElementById('2007.03220v1-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 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.00402">arXiv:1912.00402</a> <span> [<a href="https://arxiv.org/pdf/1912.00402">pdf</a>, <a href="https://arxiv.org/format/1912.00402">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="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</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/10.23919/DATE.2019.8714788">10.23919/DATE.2019.8714788 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shuhan Zhang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+C">Changhao Yan</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+D">Dian Zhou</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+X">Xuan Zeng</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="1912.00402v1-abstract-short" style="display: inline;"> Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can al… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00402v1-abstract-full').style.display = 'inline'; document.getElementById('1912.00402v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.00402v1-abstract-full" style="display: none;"> Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can also be derived from a weight space view, where the original data are mapped to feature space, and the kernel function is defined as the inner product of nonlinear features. In this paper, we propose a Bayesian optimization approach for analog circuit synthesis using neural network. We use deep neural network to extract good feature representations, and then define Gaussian process using the extracted features. Model averaging method is applied to improve the quality of uncertainty prediction. Compared to Gaussian process model with explicitly defined kernel functions, the neural-network-based Gaussian process model can automatically learn a kernel function from data, which makes it possible to provide more accurate predictions and thus accelerate the follow-up optimization procedure. Also, the neural-network-based model has O(N) training time and constant prediction time. The efficiency of the proposed method has been verified by two real-world analog circuits. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00402v1-abstract-full').style.display = 'none'; document.getElementById('1912.00402v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.05615">arXiv:1905.05615</a> <span> [<a href="https://arxiv.org/pdf/1905.05615">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="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> Transfer Learning for Scientific Data Chain Extraction in Small Chemical Corpus with BERT-CRF Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pang%2C+N">Na Pang</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+L">Li Qian</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weimin Lyu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jin-Dong Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1905.05615v1-abstract-short" style="display: inline;"> Computational chemistry develops fast in recent years due to the rapid growth and breakthroughs in AI. Thanks for the progress in natural language processing, researchers can extract more fine-grained knowledge in publications to stimulate the development in computational chemistry. While the works and corpora in chemical entity extraction have been restricted in the biomedicine or life science fi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.05615v1-abstract-full').style.display = 'inline'; document.getElementById('1905.05615v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.05615v1-abstract-full" style="display: none;"> Computational chemistry develops fast in recent years due to the rapid growth and breakthroughs in AI. Thanks for the progress in natural language processing, researchers can extract more fine-grained knowledge in publications to stimulate the development in computational chemistry. While the works and corpora in chemical entity extraction have been restricted in the biomedicine or life science field instead of the chemistry field, we build a new corpus in chemical bond field annotated for 7 types of entities: compound, solvent, method, bond, reaction, pKa and pKa value. This paper presents a novel BERT-CRF model to build scientific chemical data chains by extracting 7 chemical entities and relations from publications. And we propose a joint model to extract the entities and relations simultaneously. Experimental results on our Chemical Special Corpus demonstrate that we achieve state-of-art and competitive NER performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.05615v1-abstract-full').style.display = 'none'; document.getElementById('1905.05615v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.06423">arXiv:1806.06423</a> <span> [<a href="https://arxiv.org/pdf/1806.06423">pdf</a>, <a href="https://arxiv.org/format/1806.06423">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+C+-+H">C. -H. Huck Yang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jia-Hong Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+F">Fangyu Liu</a>, <a href="/search/cs?searchtype=author&query=Chiu%2C+F">Fang-Yi Chiu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+M">Mengya Gao</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+W">Weifeng Lyu</a>, <a href="/search/cs?searchtype=author&query=D.%2C+I+L+M">I-Hung Lin M. D.</a>, <a href="/search/cs?searchtype=author&query=Tegner%2C+J">Jesper Tegner</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="1806.06423v1-abstract-short" style="display: inline;"> Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. We propose a novel visual-assisted diagnosis hybrid model based on the support vector machine (SVM) and deep neural networks (DNNs). The model incorporates complementary strengths of DNNs and SVM. Furthermore, we present a new clinical retina lab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.06423v1-abstract-full').style.display = 'inline'; document.getElementById('1806.06423v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.06423v1-abstract-full" style="display: none;"> Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. We propose a novel visual-assisted diagnosis hybrid model based on the support vector machine (SVM) and deep neural networks (DNNs). The model incorporates complementary strengths of DNNs and SVM. Furthermore, we present a new clinical retina label collection for ophthalmology incorporating 32 retina diseases classes. Using EyeNet, our model achieves 89.73% diagnosis accuracy and the model performance is comparable to the professional ophthalmologists. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.06423v1-abstract-full').style.display = 'none'; document.getElementById('1806.06423v1-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 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at the Joint ICML and IJCAI Workshop on Computational Biology (ICML-IJCAI WCB) to be held in Stockholm SWEDEN, 2018. Referring to https://sites.google.com/view/wcb2018/accepted-papers?authuser=0</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ICML-IJCAI Workshop 2018 </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=Lyu%2C+W&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lyu%2C+W&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lyu%2C+W&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