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 796 results for author: <span class="mathjax">Xiao, X</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=Xiao%2C+X">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="Xiao, X"> </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=Xiao%2C+X&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="Xiao, X"> <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=Xiao%2C+X&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11505">arXiv:2411.11505</a> <span> [<a href="https://arxiv.org/pdf/2411.11505">pdf</a>, <a href="https://arxiv.org/format/2411.11505">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"> LaVin-DiT: Large Vision Diffusion Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhaoqing Wang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaobo Xia</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+R">Runnan Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Dongdong Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Changhu Wang</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+M">Mingming Gong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tongliang Liu</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="2411.11505v1-abstract-short" style="display: inline;"> This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11505v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11505v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11505v1-abstract-full" style="display: none;"> This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational autoencoder that encodes data into a continuous latent space. Second, for generative modeling, we develop a joint diffusion transformer that progressively produces vision outputs. Third, for unified multi-task training, in-context learning is implemented. Input-target pairs serve as task context, which guides the diffusion transformer to align outputs with specific tasks within the latent space. During inference, a task-specific context set and test data as queries allow LaVin-DiT to generalize across tasks without fine-tuning. Trained on extensive vision datasets, the model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks. This work introduces a novel pathway for large vision foundation models, underscoring the promising potential of diffusion transformers. The code and models will be open-sourced. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11505v1-abstract-full').style.display = 'none'; document.getElementById('2411.11505v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 7 figures, 2 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/2411.09675">arXiv:2411.09675</a> <span> [<a href="https://arxiv.org/pdf/2411.09675">pdf</a>, <a href="https://arxiv.org/format/2411.09675">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Citation Sentiment Reflects Multiscale Sociocultural Norms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaohuan Xia</a>, <a href="/search/cs?searchtype=author&query=Ouellet%2C+M">Mathieu Ouellet</a>, <a href="/search/cs?searchtype=author&query=Patankar%2C+S+P">Shubhankar P. Patankar</a>, <a href="/search/cs?searchtype=author&query=Tamir%2C+D+I">Diana I. Tamir</a>, <a href="/search/cs?searchtype=author&query=Bassett%2C+D+S">Dani S. Bassett</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="2411.09675v1-abstract-short" style="display: inline;"> Modern science is formally structured around scholarly publication, where scientific knowledge is canonized through citation. Precisely how citations are given and accrued can provide information about the value of discovery, the history of scientific ideas, the structure of fields, and the space or scope of inquiry. Yet parsing this information has been challenging because citations are not simpl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09675v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09675v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09675v1-abstract-full" style="display: none;"> Modern science is formally structured around scholarly publication, where scientific knowledge is canonized through citation. Precisely how citations are given and accrued can provide information about the value of discovery, the history of scientific ideas, the structure of fields, and the space or scope of inquiry. Yet parsing this information has been challenging because citations are not simply present or absent; rather, they differ in purpose, function, and sentiment. In this paper, we investigate how critical and favorable sentiments are distributed across citations, and demonstrate that citation sentiment tracks sociocultural norms across scales of collaboration, discipline, and country. At the smallest scale of individuals, we find that researchers cite scholars they have collaborated with more favorably (and less critically) than scholars they have not collaborated with. Outside collaborative relationships, higher h-index scholars cite lower h-index scholars more critically. At the mesoscale of disciplines, we find that wetlab disciplines tend to be less critical than drylab disciplines, and disciplines that engage in more synthesis through publishing more review articles tend to be less critical. At the largest scale of countries, we find that greater individualism (and lesser acceptance of the unequal distribution of power) is associated with more critical sentiment. Collectively, our results demonstrate how sociocultural factors can explain variations in sentiment in scientific communication. As such, our study contributes to the broader understanding of how human factors influence the practice of science, and underscore the importance of considering the larger sociocultural contexts in which science progresses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09675v1-abstract-full').style.display = 'none'; document.getElementById('2411.09675v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 8 figures in main; 13 pages, 3 figures in supplement</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09356">arXiv:2411.09356</a> <span> [<a href="https://arxiv.org/pdf/2411.09356">pdf</a>, <a href="https://arxiv.org/format/2411.09356">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Multi-scale Generative Modeling for Fast Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiongye Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shixuan Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+L">Luzhe Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Gengshuo Liu</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Trung-Kien Nguyen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yi Huang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+D">Di Chang</a>, <a href="/search/cs?searchtype=author&query=Kochenderfer%2C+M+J">Mykel J. Kochenderfer</a>, <a href="/search/cs?searchtype=author&query=Bogdan%2C+P">Paul Bogdan</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="2411.09356v1-abstract-short" style="display: inline;"> While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavelet domain offers a promising alternative. However, within the wavelet domain, we encounter unique challenges, especially the sparse representation of high-frequency coefficients, wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09356v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09356v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09356v1-abstract-full" style="display: none;"> While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavelet domain offers a promising alternative. However, within the wavelet domain, we encounter unique challenges, especially the sparse representation of high-frequency coefficients, which deviates significantly from the Gaussian assumptions in the diffusion process. To this end, we propose a multi-scale generative modeling in the wavelet domain that employs distinct strategies for handling low and high-frequency bands. In the wavelet domain, we apply score-based generative modeling with well-conditioned scores for low-frequency bands, while utilizing a multi-scale generative adversarial learning for high-frequency bands. As supported by the theoretical analysis and experimental results, our model significantly improve performance and reduce the number of trainable parameters, sampling steps, and time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09356v1-abstract-full').style.display = 'none'; document.getElementById('2411.09356v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06971">arXiv:2411.06971</a> <span> [<a href="https://arxiv.org/pdf/2411.06971">pdf</a>, <a href="https://arxiv.org/format/2411.06971">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"> MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical Maps </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xue Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Daiwei Zhang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+W">Wenxuan Song</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wei Huang</a>, <a href="/search/cs?searchtype=author&query=Hurni%2C+L">Lorenz Hurni</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="2411.06971v1-abstract-short" style="display: inline;"> Automated feature detection in historical maps can significantly accelerate the reconstruction of the geospatial past. However, this process is often constrained by the time-consuming task of manually digitizing sufficient high-quality training data. The emergence of visual foundation models, such as the Segment Anything Model (SAM), offers a promising solution due to their remarkable generalizati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06971v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06971v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06971v1-abstract-full" style="display: none;"> Automated feature detection in historical maps can significantly accelerate the reconstruction of the geospatial past. However, this process is often constrained by the time-consuming task of manually digitizing sufficient high-quality training data. The emergence of visual foundation models, such as the Segment Anything Model (SAM), offers a promising solution due to their remarkable generalization capabilities and rapid adaptation to new data distributions. Despite this, directly applying SAM in a zero-shot manner to historical map segmentation poses significant challenges, including poor recognition of certain geospatial features and a reliance on input prompts, which limits its ability to be fully automated. To address these challenges, we introduce MapSAM, a parameter-efficient fine-tuning strategy that adapts SAM into a prompt-free and versatile solution for various downstream historical map segmentation tasks. Specifically, we employ Weight-Decomposed Low-Rank Adaptation (DoRA) to integrate domain-specific knowledge into the image encoder. Additionally, we develop an automatic prompt generation process, eliminating the need for manual input. We further enhance the positional prompt in SAM, transforming it into a higher-level positional-semantic prompt, and modify the cross-attention mechanism in the mask decoder with masked attention for more effective feature aggregation. The proposed MapSAM framework demonstrates promising performance across two distinct historical map segmentation tasks: one focused on linear features and the other on areal features. Experimental results show that it adapts well to various features, even when fine-tuned with extremely limited data (e.g. 10 shots). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06971v1-abstract-full').style.display = 'none'; document.getElementById('2411.06971v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06339">arXiv:2411.06339</a> <span> [<a href="https://arxiv.org/pdf/2411.06339">pdf</a>, <a href="https://arxiv.org/ps/2411.06339">ps</a>, <a href="https://arxiv.org/format/2411.06339">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Probabilistic Shaped Multilevel Polar Coding for Wiretap Channel </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shen%2C+L">Li Shen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yongpeng Wu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+P">Peihong Yuan</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+C">Chengshan Xiao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiang-Gen Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenjun 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="2411.06339v1-abstract-short" style="display: inline;"> A wiretap channel is served as the fundamental model of physical layer security techniques, where the secrecy capacity of the Gaussian wiretap channel is proven to be achieved by Gaussian input. However, there remains a gap between the Gaussian secrecy capacity and the secrecy rate with conventional uniformly distributed discrete constellation input, e.g. amplitude shift keying (ASK) and quadratur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06339v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06339v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06339v1-abstract-full" style="display: none;"> A wiretap channel is served as the fundamental model of physical layer security techniques, where the secrecy capacity of the Gaussian wiretap channel is proven to be achieved by Gaussian input. However, there remains a gap between the Gaussian secrecy capacity and the secrecy rate with conventional uniformly distributed discrete constellation input, e.g. amplitude shift keying (ASK) and quadrature amplitude modulation (QAM). In this paper, we propose a probabilistic shaped multilevel polar coding scheme to bridge the gap. Specifically, the input distribution optimization problem for maximizing the secrecy rate with ASK/QAM input is solved. Numerical results show that the resulting sub-optimal solution can still approach the Gaussian secrecy capacity. Then, we investigate the polarization of multilevel polar codes for the asymmetric discrete memoryless wiretap channel, and thus propose a multilevel polar coding scheme integration with probabilistic shaping. It is proved that the scheme can achieve the secrecy capacity of the Gaussian wiretap channel with discrete constellation input, and satisfies the reliability condition and weak security condition. A security-oriented polar code construction method to natively satisfies the leakage-based security condition is also investigated. Simulation results show that the proposed scheme achieves more efficient and secure transmission than the uniform constellation input case over both the Gaussian wiretap channel and the Rayleigh fading wiretap channel. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06339v1-abstract-full').style.display = 'none'; document.getElementById('2411.06339v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE JSAC NGAT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04693">arXiv:2411.04693</a> <span> [<a href="https://arxiv.org/pdf/2411.04693">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Reciprocal Point Learning Network with Large Electromagnetic Kernel for SAR Open-Set Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiayang Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhuoxuan Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jiacheng Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haipeng 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="2411.04693v1-abstract-short" style="display: inline;"> The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04693v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04693v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04693v1-abstract-full" style="display: none;"> The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as "unknown." The chief challenge in OSR involves concurrently mitigating risks associated with generalizing features from a restricted set of known classes to numerous unknown samples and the open space exposure to potential unknown data. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature learning framework is constructed based on reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design convolutional kernels based on large-sized attribute scattering center models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments on the MSTAR datasets substantiate the superior performance of the proposed approach called ASC-RPL over mainstream methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04693v1-abstract-full').style.display = 'none'; document.getElementById('2411.04693v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01597">arXiv:2411.01597</a> <span> [<a href="https://arxiv.org/pdf/2411.01597">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> OSAD: Open-Set Aircraft Detection in SAR Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiayang Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhuoxuan Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haipeng 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="2411.01597v1-abstract-short" style="display: inline;"> Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01597v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01597v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01597v1-abstract-full" style="display: none;"> Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classification risk of known categories under strong supervision. To address these challenges, a novel open-set aircraft detector for SAR images is proposed, named Open-Set Aircraft Detection (OSAD), which is equipped with three dedicated components: global context modeling (GCM), location quality-driven pseudo labeling generation (LPG), and prototype contrastive learning (PCL). GCM effectively enhances the network's representation of objects by attention maps which is formed through the capture of long sequential positional relationships. LPG leverages clues about object positions and shapes to optimize localization quality, avoiding overfitting to known category information and enhancing generalization to potential unknown objects. PCL employs prototype-based contrastive encoding loss to promote instance-level intra-class compactness and inter-class variance, aiming to minimize the overlap between known and unknown distributions and reduce the empirical classification risk of known categories. Extensive experiments have demonstrated that the proposed method can effectively detect unknown objects and exhibit competitive performance without compromising closed-set performance. The highest absolute gain which ranges from 0 to 18.36% can be achieved on the average precision of unknown objects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01597v1-abstract-full').style.display = 'none'; document.getElementById('2411.01597v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages,11 figures. This work has been submitted to the IEEE for possible publication on March 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22482">arXiv:2410.22482</a> <span> [<a href="https://arxiv.org/pdf/2410.22482">pdf</a>, <a href="https://arxiv.org/format/2410.22482">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"> Heterogeneous Team Coordination on Partially Observable Graphs with Realistic Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yanlin Zhou</a>, <a href="/search/cs?searchtype=author&query=Limbu%2C+M">Manshi Limbu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xuan Wang</a>, <a href="/search/cs?searchtype=author&query=Shishika%2C+D">Daigo Shishika</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2410.22482v1-abstract-short" style="display: inline;"> Team Coordination on Graphs with Risky Edges (\textsc{tcgre}) is a recently proposed problem, in which robots find paths to their goals while considering possible coordination to reduce overall team cost. However, \textsc{tcgre} assumes that the \emph{entire} environment is available to a \emph{homogeneous} robot team with \emph{ubiquitous} communication. In this paper, we study an extended versio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22482v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22482v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22482v1-abstract-full" style="display: none;"> Team Coordination on Graphs with Risky Edges (\textsc{tcgre}) is a recently proposed problem, in which robots find paths to their goals while considering possible coordination to reduce overall team cost. However, \textsc{tcgre} assumes that the \emph{entire} environment is available to a \emph{homogeneous} robot team with \emph{ubiquitous} communication. In this paper, we study an extended version of \textsc{tcgre}, called \textsc{hpr-tcgre}, with three relaxations: Heterogeneous robots, Partial observability, and Realistic communication. To this end, we form a new combinatorial optimization problem on top of \textsc{tcgre}. After analysis, we divide it into two sub-problems, one for robots moving individually, another for robots in groups, depending on their communication availability. Then, we develop an algorithm that exploits real-time partial maps to solve local shortest path(s) problems, with a A*-like sub-goal(s) assignment mechanism that explores potential coordination opportunities for global interests. Extensive experiments indicate that our algorithm is able to produce team coordination behaviors in order to reduce overall cost even with our three relaxations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22482v1-abstract-full').style.display = 'none'; document.getElementById('2410.22482v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21909">arXiv:2410.21909</a> <span> [<a href="https://arxiv.org/pdf/2410.21909">pdf</a>, <a href="https://arxiv.org/format/2410.21909">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> SceneGenAgent: Precise Industrial Scene Generation with Coding Agent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiao Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Dan Zhang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+Z">Zibo Liao</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+Z">Zhenyu Hou</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tianrui Sun</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jing Li</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+L">Ling Fu</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yuxiao Dong</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="2410.21909v1-abstract-short" style="display: inline;"> The modeling of industrial scenes is essential for simulations in industrial manufacturing. While large language models (LLMs) have shown significant progress in generating general 3D scenes from textual descriptions, generating industrial scenes with LLMs poses a unique challenge due to their demand for precise measurements and positioning, requiring complex planning over spatial arrangement. To… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21909v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21909v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21909v1-abstract-full" style="display: none;"> The modeling of industrial scenes is essential for simulations in industrial manufacturing. While large language models (LLMs) have shown significant progress in generating general 3D scenes from textual descriptions, generating industrial scenes with LLMs poses a unique challenge due to their demand for precise measurements and positioning, requiring complex planning over spatial arrangement. To address this challenge, we introduce SceneGenAgent, an LLM-based agent for generating industrial scenes through C# code. SceneGenAgent ensures precise layout planning through a structured and calculable format, layout verification, and iterative refinement to meet the quantitative requirements of industrial scenarios. Experiment results demonstrate that LLMs powered by SceneGenAgent exceed their original performance, reaching up to 81.0% success rate in real-world industrial scene generation tasks and effectively meeting most scene generation requirements. To further enhance accessibility, we construct SceneInstruct, a dataset designed for fine-tuning open-source LLMs to integrate into SceneGenAgent. Experiments show that fine-tuning open-source LLMs on SceneInstruct yields significant performance improvements, with Llama3.1-70B approaching the capabilities of GPT-4o. Our code and data are available at https://github.com/THUDM/SceneGenAgent . <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21909v1-abstract-full').style.display = 'none'; document.getElementById('2410.21909v1-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 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/2410.17835">arXiv:2410.17835</a> <span> [<a href="https://arxiv.org/pdf/2410.17835">pdf</a>, <a href="https://arxiv.org/ps/2410.17835">ps</a>, <a href="https://arxiv.org/format/2410.17835">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"> Optimal Streaming Algorithms for Multi-Armed Bandits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jin%2C+T">Tianyuan Jin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+K">Keke Huang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jing Tang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiaokui Xiao</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="2410.17835v1-abstract-short" style="display: inline;"> This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of $n$ arms with reward distributions supported on $[0,1]$ with unknown means. The arms in the stream are arriving one by one, and the algorithm cannot access an arm unless it is stored in a limited size memory. We first study the streaming \eps-$top$-$k$ arms identifica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17835v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17835v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17835v1-abstract-full" style="display: none;"> This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of $n$ arms with reward distributions supported on $[0,1]$ with unknown means. The arms in the stream are arriving one by one, and the algorithm cannot access an arm unless it is stored in a limited size memory. We first study the streaming \eps-$top$-$k$ arms identification problem, which asks for $k$ arms whose reward means are lower than that of the $k$-th best arm by at most $\eps$ with probability at least $1-未$. For general $\eps \in (0,1)$, the existing solution for this problem assumes $k = 1$ and achieves the optimal sample complexity $O(\frac{n}{\eps^2} \log \frac{1}未)$ using $O(\log^*(n))$ ($\log^*(n)$ equals the number of times that we need to apply the logarithm function on $n$ before the results is no more than 1.) memory and a single pass of the stream. We propose an algorithm that works for any $k$ and achieves the optimal sample complexity $O(\frac{n}{\eps^2} \log\frac{k}未)$ using a single-arm memory and a single pass of the stream. Second, we study the streaming BAI problem, where the objective is to identify the arm with the maximum reward mean with at least $1-未$ probability, using a single-arm memory and as few passes of the input stream as possible. We present a single-arm-memory algorithm that achieves a near instance-dependent optimal sample complexity within $O(\log 螖_2^{-1})$ passes, where $螖_2$ is the gap between the mean of the best arm and that of the second best arm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17835v1-abstract-full').style.display = 'none'; document.getElementById('2410.17835v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">24pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ICML2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16603">arXiv:2410.16603</a> <span> [<a href="https://arxiv.org/pdf/2410.16603">pdf</a>, <a href="https://arxiv.org/format/2410.16603">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Efficient and Effective Algorithms for A Family of Influence Maximization Problems with A Matroid Constraint </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yiqian Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shiqi Zhang</a>, <a href="/search/cs?searchtype=author&query=Lakshmanan%2C+L+V+S">Laks V. S. Lakshmanan</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+W">Wenqing Lin</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiaokui Xiao</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+B">Bo Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.16603v1-abstract-short" style="display: inline;"> Influence maximization (IM) is a classic problem that aims to identify a small group of critical individuals, known as seeds, who can influence the largest number of users in a social network through word-of-mouth. This problem finds important applications including viral marketing, infection detection, and misinformation containment. The conventional IM problem is typically studied with the overs… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16603v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16603v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16603v1-abstract-full" style="display: none;"> Influence maximization (IM) is a classic problem that aims to identify a small group of critical individuals, known as seeds, who can influence the largest number of users in a social network through word-of-mouth. This problem finds important applications including viral marketing, infection detection, and misinformation containment. The conventional IM problem is typically studied with the oversimplified goal of selecting a single seed set. Many real-world scenarios call for multiple sets of seeds, particularly on social media platforms where various viral marketing campaigns need different sets of seeds to propagate effectively. To this end, previous works have formulated various IM variants, central to which is the requirement of multiple seed sets, naturally modeled as a matroid constraint. However, the current best-known solutions for these variants either offer a weak $(1/2-蔚)$-approximation, or offer a $(1-1/e-蔚)$-approximation algorithm that is very expensive. We propose an efficient seed selection method called AMP, an algorithm with a $(1-1/e-蔚)$-approximation guarantee for this family of IM variants. To further improve efficiency, we also devise a fast implementation, called RAMP. We extensively evaluate the performance of our proposal against 6 competitors across 4 IM variants and on 7 real-world networks, demonstrating that our proposal outperforms all competitors in terms of result quality, running time, and memory usage. We have also deployed RAMP in a real industry strength application involving online gaming, where we show that our deployed solution significantly improves upon the baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16603v1-abstract-full').style.display = 'none'; document.getElementById('2410.16603v1-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">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The technical report of the paper entitled 'Efficient and Effective Algorithms for A Family of Influence Maximization Problems with A Matroid Constraint' in PVLDB'25</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13110">arXiv:2410.13110</a> <span> [<a href="https://arxiv.org/pdf/2410.13110">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </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/s11432-023-4127-5">10.1007/s11432-023-4127-5 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiangping Chen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xing Hu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yuan Huang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+H">He Jiang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+W">Weixing Ji</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yanjie Jiang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yanyan Jiang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hui Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaochen Li</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+X">Xiaoli Lian</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+G">Guozhu Meng</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+X">Xin Peng</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Hailong Sun</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+L">Lin Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bo Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chong Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiayi Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+T">Tiantian Wang</a>, <a href="/search/cs?searchtype=author&query=Xuan%2C+J">Jifeng Xuan</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yibiao Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yixin Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yuming Zhou</a> , et al. (1 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13110v1-abstract-short" style="display: inline;"> Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13110v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13110v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13110v1-abstract-full" style="display: none;"> Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many papers have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However, although several surveys have provided overall pictures of the application of deep learning techniques in software engineering, they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this paper, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out the through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13110v1-abstract-full').style.display = 'none'; document.getElementById('2410.13110v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in SCIENCE CHINA Information Sciences</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11528">arXiv:2410.11528</a> <span> [<a href="https://arxiv.org/pdf/2410.11528">pdf</a>, <a href="https://arxiv.org/format/2410.11528">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3680528.3687582">10.1145/3680528.3687582 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Hairmony: Fairness-aware hairstyle classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meishvili%2C+G">Givi Meishvili</a>, <a href="/search/cs?searchtype=author&query=Clemoes%2C+J">James Clemoes</a>, <a href="/search/cs?searchtype=author&query=Hewitt%2C+C">Charlie Hewitt</a>, <a href="/search/cs?searchtype=author&query=Hosenie%2C+Z">Zafiirah Hosenie</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xian Xiao</a>, <a href="/search/cs?searchtype=author&query=de+La+Gorce%2C+M">Martin de La Gorce</a>, <a href="/search/cs?searchtype=author&query=Takacs%2C+T">Tibor Takacs</a>, <a href="/search/cs?searchtype=author&query=Baltrusaitis%2C+T">Tadas Baltrusaitis</a>, <a href="/search/cs?searchtype=author&query=Criminisi%2C+A">Antonio Criminisi</a>, <a href="/search/cs?searchtype=author&query=McRae%2C+C">Chyna McRae</a>, <a href="/search/cs?searchtype=author&query=Jablonski%2C+N">Nina Jablonski</a>, <a href="/search/cs?searchtype=author&query=Wilczkowiak%2C+M">Marta Wilczkowiak</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="2410.11528v1-abstract-short" style="display: inline;"> We present a method for prediction of a person's hairstyle from a single image. Despite growing use cases in user digitization and enrollment for virtual experiences, available methods are limited, particularly in the range of hairstyles they can capture. Human hair is extremely diverse and lacks any universally accepted description or categorization, making this a challenging task. Most current m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11528v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11528v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11528v1-abstract-full" style="display: none;"> We present a method for prediction of a person's hairstyle from a single image. Despite growing use cases in user digitization and enrollment for virtual experiences, available methods are limited, particularly in the range of hairstyles they can capture. Human hair is extremely diverse and lacks any universally accepted description or categorization, making this a challenging task. Most current methods rely on parametric models of hair at a strand level. These approaches, while very promising, are not yet able to represent short, frizzy, coily hair and gathered hairstyles. We instead choose a classification approach which can represent the diversity of hairstyles required for a truly robust and inclusive system. Previous classification approaches have been restricted by poorly labeled data that lacks diversity, imposing constraints on the usefulness of any resulting enrollment system. We use only synthetic data to train our models. This allows for explicit control of diversity of hairstyle attributes, hair colors, facial appearance, poses, environments and other parameters. It also produces noise-free ground-truth labels. We introduce a novel hairstyle taxonomy developed in collaboration with a diverse group of domain experts which we use to balance our training data, supervise our model, and directly measure fairness. We annotate our synthetic training data and a real evaluation dataset using this taxonomy and release both to enable comparison of future hairstyle prediction approaches. We employ an architecture based on a pre-trained feature extraction network in order to improve generalization of our method to real data and predict taxonomy attributes as an auxiliary task to improve accuracy. Results show our method to be significantly more robust for challenging hairstyles than recent parametric approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11528v1-abstract-full').style.display = 'none'; document.getElementById('2410.11528v1-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 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/2410.10128">arXiv:2410.10128</a> <span> [<a href="https://arxiv.org/pdf/2410.10128">pdf</a>, <a href="https://arxiv.org/format/2410.10128">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaoyu Xia</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Ziqi Wang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+R">Ruoxi Sun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bowen Liu</a>, <a href="/search/cs?searchtype=author&query=Khalil%2C+I">Ibrahim Khalil</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+M">Minhui Xue</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="2410.10128v2-abstract-short" style="display: inline;"> The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize information from the training data, increasing the potential privacy risk to users. To address this, multiple machine unlearning techniques have been developed and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10128v2-abstract-full').style.display = 'inline'; document.getElementById('2410.10128v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10128v2-abstract-full" style="display: none;"> The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize information from the training data, increasing the potential privacy risk to users. To address this, multiple machine unlearning techniques have been developed and deployed. Among them, approximate unlearning is a popular solution, but recent studies report that its unlearning effectiveness is not fully guaranteed. Another approach, exact unlearning, tackles this issue by discarding the data and retraining the model from scratch, but at the cost of considerable computational and memory resources. However, not all devices have the capability to perform such retraining. In numerous machine learning applications, such as edge devices, Internet-of-Things (IoT), mobile devices, and satellites, resources are constrained, posing challenges for deploying existing exact unlearning methods. In this study, we propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE), an approach to enabling exact unlearning on resource-constrained devices. Aiming to minimize the retrain overhead by storing sub-models on the resource-constrained device, CAUSE innovatively applies a Fibonacci-based replacement strategy and updates the number of shards adaptively in the user-based data partition process. To further improve the effectiveness of memory usage, CAUSE leverages the advantage of model pruning to save memory via compression with minimal accuracy sacrifice. The experimental results demonstrate that CAUSE significantly outperforms other representative systems in realizing exact unlearning on the resource-constrained device by 9.23%-80.86%, 66.21%-83.46%, and 5.26%-194.13% in terms of unlearning speed, energy consumption, and accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10128v2-abstract-full').style.display = 'none'; document.getElementById('2410.10128v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE Symposium on Security and Privacy 2025 (Oakland 2025)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07588">arXiv:2410.07588</a> <span> [<a href="https://arxiv.org/pdf/2410.07588">pdf</a>, <a href="https://arxiv.org/format/2410.07588">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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Careful About What App Promotion Ads Recommend! Detecting and Explaining Malware Promotion via App Promotion Graph </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+S">Shang Ma</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chaoran Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shao Yang</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+S">Shifu Hou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T+J">Toby Jia-Jun Li</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xusheng Xiao</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+T">Tao Xie</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yanfang Ye</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="2410.07588v1-abstract-short" style="display: inline;"> In Android apps, their developers frequently place app promotion ads, namely advertisements to promote other apps. Unfortunately, the inadequate vetting of ad content allows malicious developers to exploit app promotion ads as a new distribution channel for malware. To help detect malware distributed via app promotion ads, in this paper, we propose a novel approach, named ADGPE, that synergistical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07588v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07588v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07588v1-abstract-full" style="display: none;"> In Android apps, their developers frequently place app promotion ads, namely advertisements to promote other apps. Unfortunately, the inadequate vetting of ad content allows malicious developers to exploit app promotion ads as a new distribution channel for malware. To help detect malware distributed via app promotion ads, in this paper, we propose a novel approach, named ADGPE, that synergistically integrates app user interface (UI) exploration with graph learning to automatically collect app promotion ads, detect malware promoted by these ads, and explain the promotion mechanisms employed by the detected malware. Our evaluation on 18, 627 app promotion ads demonstrates the substantial risks in the app promotion ecosystem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07588v1-abstract-full').style.display = 'none'; document.getElementById('2410.07588v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NDSS Symposium 2025 Accepted Papers</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06515">arXiv:2410.06515</a> <span> [<a href="https://arxiv.org/pdf/2410.06515">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Studying Practitioners' Expectations on Clear Code Review Comments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenhao Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junkai Chen</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Q">Qiheng Mao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xing Hu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kui Liu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</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="2410.06515v1-abstract-short" style="display: inline;"> The code review comment (CRC) is pivotal in the process of modern code review. It provides reviewers with the opportunity to identify potential bugs, offer constructive feedback, and suggest improvements. Clear and concise code review comments (CRCs) facilitate the communication between developers and is crucial to the correct understanding of the issues identified and proposed solutions. Despite… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06515v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06515v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06515v1-abstract-full" style="display: none;"> The code review comment (CRC) is pivotal in the process of modern code review. It provides reviewers with the opportunity to identify potential bugs, offer constructive feedback, and suggest improvements. Clear and concise code review comments (CRCs) facilitate the communication between developers and is crucial to the correct understanding of the issues identified and proposed solutions. Despite the importance of CRCs' clarity, there is still a lack of guidelines on what constitutes a good clarity and how to evaluate it. In this paper, we conduct a comprehensive study on understanding and evaluating the clarity of CRCs. We first derive a set of attributes related to the clarity of CRCs, namely RIE attributes (i.e., Relevance, Informativeness, and Expression), as well as their corresponding evaluation criteria based on our literature review and survey with practitioners. We then investigate the clarity of CRCs in open-source projects written in nine programming languages and find that a large portion (i.e., 28.8%) of the CRCs lack the clarity in at least one of the attributes. Finally, we propose ClearCRC, an automated framework that evaluates the clarity of CRCs. Experimental results show that ClearCRC can effectively evaluate the clarity of CRCs and outperform the baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06515v1-abstract-full').style.display = 'none'; document.getElementById('2410.06515v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04684">arXiv:2410.04684</a> <span> [<a href="https://arxiv.org/pdf/2410.04684">pdf</a>, <a href="https://arxiv.org/format/2410.04684">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Combining Structural and Unstructured Data: A Topic-based Finite Mixture Model for Insurance Claim Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hou%2C+Y">Yanxi Hou</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaolan Xia</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+G">Guangyuan Gao</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="2410.04684v1-abstract-short" style="display: inline;"> Modeling insurance claim amounts and classifying claims into different risk levels are critical yet challenging tasks. Traditional predictive models for insurance claims often overlook the valuable information embedded in claim descriptions. This paper introduces a novel approach by developing a joint mixture model that integrates both claim descriptions and claim amounts. Our method establishes a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04684v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04684v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04684v1-abstract-full" style="display: none;"> Modeling insurance claim amounts and classifying claims into different risk levels are critical yet challenging tasks. Traditional predictive models for insurance claims often overlook the valuable information embedded in claim descriptions. This paper introduces a novel approach by developing a joint mixture model that integrates both claim descriptions and claim amounts. Our method establishes a probabilistic link between textual descriptions and loss amounts, enhancing the accuracy of claims clustering and prediction. In our proposed model, the latent topic/component indicator serves as a proxy for both the thematic content of the claim description and the component of loss distributions. Specifically, conditioned on the topic/component indicator, the claim description follows a multinomial distribution, while the claim amount follows a component loss distribution. We propose two methods for model calibration: an EM algorithm for maximum a posteriori estimates, and an MH-within-Gibbs sampler algorithm for the posterior distribution. The empirical study demonstrates that the proposed methods work effectively, providing interpretable claims clustering and prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04684v1-abstract-full').style.display = 'none'; document.getElementById('2410.04684v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04439">arXiv:2410.04439</a> <span> [<a href="https://arxiv.org/pdf/2410.04439">pdf</a>, <a href="https://arxiv.org/format/2410.04439">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenbo Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Guohao Li</a>, <a href="/search/cs?searchtype=author&query=Lan%2C+Z">Zhibin Lan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xue Xu</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+W">Wanru Zhuang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiachen Liu</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xinyan Xiao</a>, <a href="/search/cs?searchtype=author&query=Su%2C+J">Jinsong Su</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="2410.04439v1-abstract-short" style="display: inline;"> Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text, but their development shows promising potential. In this paper, we propose a series of methods, aiming to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04439v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04439v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04439v1-abstract-full" style="display: none;"> Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text, but their development shows promising potential. In this paper, we propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese. We first conduct a preliminary study revealing that Byte Pair Encoding (BPE) tokenization and the insufficient learning of cross-attention modules restrict the performance of the backbone models. Based on these observations, we make the following improvements: (1) We design a mixed granularity input strategy to provide more suitable text representations; (2) We propose to augment the conventional training objective with three glyph-aware training losses, which enhance the learning of cross-attention modules and encourage the model to focus on visual texts. Through experiments, we demonstrate that our methods can effectively empower backbone models to generate semantic relevant, aesthetically appealing, and accurate visual text images, while maintaining their fundamental image generation quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04439v1-abstract-full').style.display = 'none'; document.getElementById('2410.04439v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03559">arXiv:2410.03559</a> <span> [<a href="https://arxiv.org/pdf/2410.03559">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Optimizing food taste sensory evaluation through neural network-based taste electroencephalogram channel selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiuxin Xia</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qun Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">He Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chenrui Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pengwei Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yan Shi</a>, <a href="/search/cs?searchtype=author&query=Men%2C+H">Hong Men</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="2410.03559v1-abstract-short" style="display: inline;"> The taste electroencephalogram (EEG) evoked by the taste stimulation can reflect different brain patterns and be used in applications such as sensory evaluation of food. However, considering the computational cost and efficiency, EEG data with many channels has to face the critical issue of channel selection. This paper proposed a channel selection method called class activation mapping with atten… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03559v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03559v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03559v1-abstract-full" style="display: none;"> The taste electroencephalogram (EEG) evoked by the taste stimulation can reflect different brain patterns and be used in applications such as sensory evaluation of food. However, considering the computational cost and efficiency, EEG data with many channels has to face the critical issue of channel selection. This paper proposed a channel selection method called class activation mapping with attention (CAM-Attention). The CAM-Attention method combined a convolutional neural network with channel and spatial attention (CNN-CSA) model with a gradient-weighted class activation mapping (Grad-CAM) model. The CNN-CSA model exploited key features in EEG data by attention mechanism, and the Grad-CAM model effectively realized the visualization of feature regions. Then, channel selection was effectively implemented based on feature regions. Finally, the CAM-Attention method reduced the computational burden of taste EEG recognition and effectively distinguished the four tastes. In short, it has excellent recognition performance and provides effective technical support for taste sensory evaluation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03559v1-abstract-full').style.display = 'none'; document.getElementById('2410.03559v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">33 pages, 13 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/2410.02250">arXiv:2410.02250</a> <span> [<a href="https://arxiv.org/pdf/2410.02250">pdf</a>, <a href="https://arxiv.org/format/2410.02250">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Probabilistic road classification in historical maps using synthetic data and deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=M%C3%BChlematter%2C+D+J">Dominik J. M眉hlematter</a>, <a href="/search/cs?searchtype=author&query=Schweizer%2C+S">Sebastian Schweizer</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+C">Chenjing Jiao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xue Xia</a>, <a href="/search/cs?searchtype=author&query=Heitzler%2C+M">Magnus Heitzler</a>, <a href="/search/cs?searchtype=author&query=Hurni%2C+L">Lorenz Hurni</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="2410.02250v1-abstract-short" style="display: inline;"> Historical maps are invaluable for analyzing long-term changes in transportation and spatial development, offering a rich source of data for evolutionary studies. However, digitizing and classifying road networks from these maps is often expensive and time-consuming, limiting their widespread use. Recent advancements in deep learning have made automatic road extraction from historical maps feasibl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02250v1-abstract-full').style.display = 'inline'; document.getElementById('2410.02250v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02250v1-abstract-full" style="display: none;"> Historical maps are invaluable for analyzing long-term changes in transportation and spatial development, offering a rich source of data for evolutionary studies. However, digitizing and classifying road networks from these maps is often expensive and time-consuming, limiting their widespread use. Recent advancements in deep learning have made automatic road extraction from historical maps feasible, yet these methods typically require large amounts of labeled training data. To address this challenge, we introduce a novel framework that integrates deep learning with geoinformation, computer-based painting, and image processing methodologies. This framework enables the extraction and classification of roads from historical maps using only road geometries without needing road class labels for training. The process begins with training of a binary segmentation model to extract road geometries, followed by morphological operations, skeletonization, vectorization, and filtering algorithms. Synthetic training data is then generated by a painting function that artificially re-paints road segments using predefined symbology for road classes. Using this synthetic data, a deep ensemble is trained to generate pixel-wise probabilities for road classes to mitigate distribution shift. These predictions are then discretized along the extracted road geometries. Subsequently, further processing is employed to classify entire roads, enabling the identification of potential changes in road classes and resulting in a labeled road class dataset. Our method achieved completeness and correctness scores of over 94% and 92%, respectively, for road class 2, the most prevalent class in the two Siegfried Map sheets from Switzerland used for testing. This research offers a powerful tool for urban planning and transportation decision-making by efficiently extracting and classifying roads from historical maps. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02250v1-abstract-full').style.display = 'none'; document.getElementById('2410.02250v1-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 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/2410.01359">arXiv:2410.01359</a> <span> [<a href="https://arxiv.org/pdf/2410.01359">pdf</a>, <a href="https://arxiv.org/format/2410.01359">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"> FlashMask: Efficient and Rich Mask Extension of FlashAttention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guoxia Wang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+J">Jinle Zeng</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiyuan Xiao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Siming Wu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiabin Yang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+L">Lujing Zheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zeyu Chen</a>, <a href="/search/cs?searchtype=author&query=Bian%2C+J">Jiang Bian</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Dianhai Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haifeng 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="2410.01359v1-abstract-short" style="display: inline;"> The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by eliminating the $O(N^2)$ memory dependency and reducing attention latency through IO-aware memory optimizations. However, its native support for certain attention… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01359v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01359v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01359v1-abstract-full" style="display: none;"> The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by eliminating the $O(N^2)$ memory dependency and reducing attention latency through IO-aware memory optimizations. However, its native support for certain attention mask types is limited, and it does not inherently accommodate more complex masking requirements. Previous approaches resort to using dense masks with $O(N^2)$ memory complexity, leading to inefficiencies. In this paper, we propose FlashMask, an extension of FlashAttention that introduces a column-wise sparse representation of attention masks. This approach efficiently represents a wide range of mask types and facilitates the development of optimized kernel implementations. By adopting this novel representation, FlashMask achieves linear memory complexity $O(N)$, suitable for modeling long-context sequences. Moreover, this representation enables kernel optimizations that eliminate unnecessary computations by leveraging sparsity in the attention mask, without sacrificing computational accuracy, resulting in higher computational efficiency. We evaluate FlashMask's performance in fine-tuning and alignment training of LLMs such as SFT, LoRA, DPO, and RM. FlashMask achieves significant throughput improvements, with end-to-end speedups ranging from 1.65x to 3.22x compared to existing FlashAttention dense method. Additionally, our kernel-level comparisons demonstrate that FlashMask surpasses the latest counterpart, FlexAttention, by 12.1% to 60.7% in terms of kernel TFLOPs/s, achieving 37.8% to 62.3% of the theoretical maximum FLOPs/s on the A100 GPU. The code is open-sourced on PaddlePaddle and integrated into PaddleNLP, supporting models with over 100 billion parameters for contexts up to 128K tokens. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01359v1-abstract-full').style.display = 'none'; document.getElementById('2410.01359v1-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/2410.01105">arXiv:2410.01105</a> <span> [<a href="https://arxiv.org/pdf/2410.01105">pdf</a>, <a href="https://arxiv.org/format/2410.01105">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"> M2P2: A Multi-Modal Passive Perception Dataset for Off-Road Mobility in Extreme Low-Light Conditions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Datar%2C+A">Aniket Datar</a>, <a href="/search/cs?searchtype=author&query=Pokhrel%2C+A">Anuj Pokhrel</a>, <a href="/search/cs?searchtype=author&query=Nazeri%2C+M">Mohammad Nazeri</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+M+B">Madhan B. Rao</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yufan Zhang</a>, <a href="/search/cs?searchtype=author&query=Harrison%2C+A">Andre Harrison</a>, <a href="/search/cs?searchtype=author&query=Wigness%2C+M">Maggie Wigness</a>, <a href="/search/cs?searchtype=author&query=Osteen%2C+P+R">Philip R. Osteen</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jinwei Ye</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2410.01105v1-abstract-short" style="display: inline;"> Long-duration, off-road, autonomous missions require robots to continuously perceive their surroundings regardless of the ambient lighting conditions. Most existing autonomy systems heavily rely on active sensing, e.g., LiDAR, RADAR, and Time-of-Flight sensors, or use (stereo) visible light imaging sensors, e.g., color cameras, to perceive environment geometry and semantics. In scenarios where ful… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01105v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01105v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01105v1-abstract-full" style="display: none;"> Long-duration, off-road, autonomous missions require robots to continuously perceive their surroundings regardless of the ambient lighting conditions. Most existing autonomy systems heavily rely on active sensing, e.g., LiDAR, RADAR, and Time-of-Flight sensors, or use (stereo) visible light imaging sensors, e.g., color cameras, to perceive environment geometry and semantics. In scenarios where fully passive perception is required and lighting conditions are degraded to an extent that visible light cameras fail to perceive, most downstream mobility tasks such as obstacle avoidance become impossible. To address such a challenge, this paper presents a Multi-Modal Passive Perception dataset, M2P2, to enable off-road mobility in low-light to no-light conditions. We design a multi-modal sensor suite including thermal, event, and stereo RGB cameras, GPS, two Inertia Measurement Units (IMUs), as well as a high-resolution LiDAR for ground truth, with a novel multi-sensor calibration procedure that can efficiently transform multi-modal perceptual streams into a common coordinate system. Our 10-hour, 32 km dataset also includes mobility data such as robot odometry and actions and covers well-lit, low-light, and no-light conditions, along with paved, on-trail, and off-trail terrain. Our results demonstrate that off-road mobility is possible through only passive perception in extreme low-light conditions using end-to-end learning and classical planning. The project website can be found at https://cs.gmu.edu/~xiao/Research/M2P2/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01105v1-abstract-full').style.display = 'none'; document.getElementById('2410.01105v1-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 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/2409.20424">arXiv:2409.20424</a> <span> [<a href="https://arxiv.org/pdf/2409.20424">pdf</a>, <a href="https://arxiv.org/format/2409.20424">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiacong Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+B">Bohong Wu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+H">Haiyong Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xun Zhou</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xin Xiao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Haoyuan Guo</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Jun Xiao</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="2409.20424v1-abstract-short" style="display: inline;"> Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated mul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20424v1-abstract-full').style.display = 'inline'; document.getElementById('2409.20424v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.20424v1-abstract-full" style="display: none;"> Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated multi-modal data construction pipeline that organizes the final generation output into a Python code format. The pipeline leverages the VLM itself to extract cross-modal information via different prompts and filter the generated outputs again via a consistency filtering strategy. Experiments have demonstrated the high quality of W2C by improving various existing visual question answering and visual grounding benchmarks across different VLMs. Further analysis also demonstrates that the new code parsing ability of VLMs presents better cross-modal equivalence than the commonly used detail caption ability. Our code is available at https://github.com/foundation-multimodal-models/World2Code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20424v1-abstract-full').style.display = 'none'; document.getElementById('2409.20424v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at EMNLP 2024 Main Conference, 16pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19816">arXiv:2409.19816</a> <span> [<a href="https://arxiv.org/pdf/2409.19816">pdf</a>, <a href="https://arxiv.org/format/2409.19816">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Grounded Curriculum Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+L">Linji Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zifan Xu</a>, <a href="/search/cs?searchtype=author&query=Stone%2C+P">Peter Stone</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.19816v1-abstract-short" style="display: inline;"> The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another, often-overlooked mismatch between simulations and the real world, namely the distribution of available training tasks. Such a mismatch is further exacerbated by exist… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19816v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19816v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19816v1-abstract-full" style="display: none;"> The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another, often-overlooked mismatch between simulations and the real world, namely the distribution of available training tasks. Such a mismatch is further exacerbated by existing curriculum learning techniques, which automatically vary the simulation task distribution without considering its relevance to the real world. Considering these challenges, we posit that curriculum learning for robotics RL needs to be grounded in real-world task distributions. To this end, we propose Grounded Curriculum Learning (GCL), which aligns the simulated task distribution in the curriculum with the real world, as well as explicitly considers what tasks have been given to the robot and how the robot has performed in the past. We validate GCL using the BARN dataset on complex navigation tasks, achieving a 6.8% and 6.5% higher success rate compared to a state-of-the-art CL method and a curriculum designed by human experts, respectively. These results show that GCL can enhance learning efficiency and navigation performance by grounding the simulation task distribution in the real world within an adaptive curriculum. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19816v1-abstract-full').style.display = 'none'; document.getElementById('2409.19816v1-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 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">8 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18892">arXiv:2409.18892</a> <span> [<a href="https://arxiv.org/pdf/2409.18892">pdf</a>, <a href="https://arxiv.org/format/2409.18892">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"> IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+F">Fan Lin</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+S">Shuyi Xie</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+Y">Yong Dai</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+W">Wenlin Yao</a>, <a href="/search/cs?searchtype=author&query=Lang%2C+T">Tianjiao Lang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zishan Xu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhichao Hu</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiao Xiao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuhong Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yu 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="2409.18892v2-abstract-short" style="display: inline;"> As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we prop… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18892v2-abstract-full').style.display = 'inline'; document.getElementById('2409.18892v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18892v2-abstract-full" style="display: none;"> As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework, and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18892v2-abstract-full').style.display = 'none'; document.getElementById('2409.18892v2-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 27 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">NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17479">arXiv:2409.17479</a> <span> [<a href="https://arxiv.org/pdf/2409.17479">pdf</a>, <a href="https://arxiv.org/format/2409.17479">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"> Traverse the Non-Traversable: Estimating Traversability for Wheeled Mobility on Vertically Challenging Terrain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Datar%2C+A">Aniket Datar</a>, <a href="/search/cs?searchtype=author&query=Pokhrel%2C+A">Anuj Pokhrel</a>, <a href="/search/cs?searchtype=author&query=Choulas%2C+M">Matthew Choulas</a>, <a href="/search/cs?searchtype=author&query=Nazeri%2C+M">Mohammad Nazeri</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.17479v1-abstract-short" style="display: inline;"> Most traversability estimation techniques divide off-road terrain into traversable (e.g., pavement, gravel, and grass) and non-traversable (e.g., boulders, vegetation, and ditches) regions and then inform subsequent planners to produce trajectories on the traversable part. However, recent research demonstrated that wheeled robots can traverse vertically challenging terrain (e.g., extremely rugged… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17479v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17479v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17479v1-abstract-full" style="display: none;"> Most traversability estimation techniques divide off-road terrain into traversable (e.g., pavement, gravel, and grass) and non-traversable (e.g., boulders, vegetation, and ditches) regions and then inform subsequent planners to produce trajectories on the traversable part. However, recent research demonstrated that wheeled robots can traverse vertically challenging terrain (e.g., extremely rugged boulders comparable in size to the vehicles themselves), which unfortunately would be deemed as non-traversable by existing techniques. Motivated by such limitations, this work aims at identifying the traversable from the seemingly non-traversable, vertically challenging terrain based on past kinodynamic vehicle-terrain interactions in a data-driven manner. Our new Traverse the Non-Traversable(TNT) traversability estimator can efficiently guide a down-stream sampling-based planner containing a high-precision 6-DoF kinodynamic model, which becomes deployable onboard a small-scale vehicle. Additionally, the estimated traversability can also be used as a costmap to plan global and local paths without sampling. Our experiment results show that TNT can improve planning performance, efficiency, and stability by 50%, 26.7%, and 9.2% respectively on a physical robot platform. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17479v1-abstract-full').style.display = 'none'; document.getElementById('2409.17479v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">for associated video file, see https://www.youtube.com/watch?v=Shcalb8sGcA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17469">arXiv:2409.17469</a> <span> [<a href="https://arxiv.org/pdf/2409.17469">pdf</a>, <a href="https://arxiv.org/format/2409.17469">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"> Verti-Selector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tong Xu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.17469v1-abstract-short" style="display: inline;"> Reinforcement Learning (RL) has the potential to enable extreme off-road mobility by circumventing complex kinodynamic modeling, planning, and control by simulated end-to-end trial-and-error learning experiences. However, most RL methods are sample-inefficient when training in a large amount of manually designed simulation environments and struggle at generalizing to the real world. To address the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17469v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17469v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17469v1-abstract-full" style="display: none;"> Reinforcement Learning (RL) has the potential to enable extreme off-road mobility by circumventing complex kinodynamic modeling, planning, and control by simulated end-to-end trial-and-error learning experiences. However, most RL methods are sample-inefficient when training in a large amount of manually designed simulation environments and struggle at generalizing to the real world. To address these issues, we introduce Verti-Selector (VS), an automatic curriculum learning framework designed to enhance learning efficiency and generalization by selectively sampling training terrain. VS prioritizes vertically challenging terrain with higher Temporal Difference (TD) errors when revisited, thereby allowing robots to learn at the edge of their evolving capabilities. By dynamically adjusting the sampling focus, VS significantly boosts sample efficiency and generalization within the VW-Chrono simulator built on the Chrono multi-physics engine. Furthermore, we provide simulation and physical results using VS on a Verti-4-Wheeler platform. These results demonstrate that VS can achieve 23.08% improvement in terms of success rate by efficiently sampling during training and robustly generalizing to the real world. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17469v1-abstract-full').style.display = 'none'; document.getElementById('2409.17469v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16739">arXiv:2409.16739</a> <span> [<a href="https://arxiv.org/pdf/2409.16739">pdf</a>, <a href="https://arxiv.org/format/2409.16739">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Context-Enhanced LLM-Based Framework for Automatic Test Refactoring </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yi Gao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xing Hu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaohu Yang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</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="2409.16739v1-abstract-short" style="display: inline;"> Test smells arise from poor design practices and insufficient domain knowledge, which can lower the quality of test code and make it harder to maintain and update. Manually refactoring test smells is time-consuming and error-prone, highlighting the necessity for automated approaches. Current rule-based refactoring methods often struggle in scenarios not covered by predefined rules and lack the fle… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16739v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16739v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16739v1-abstract-full" style="display: none;"> Test smells arise from poor design practices and insufficient domain knowledge, which can lower the quality of test code and make it harder to maintain and update. Manually refactoring test smells is time-consuming and error-prone, highlighting the necessity for automated approaches. Current rule-based refactoring methods often struggle in scenarios not covered by predefined rules and lack the flexibility needed to handle diverse cases effectively. In this paper, we propose a novel approach called UTRefactor, a context-enhanced, LLM-based framework for automatic test refactoring in Java projects. UTRefactor extracts relevant context from test code and leverages an external knowledge base that includes test smell definitions, descriptions, and DSL-based refactoring rules. By simulating the manual refactoring process through a chain-of-thought approach, UTRefactor guides the LLM to eliminate test smells in a step-by-step process, ensuring both accuracy and consistency throughout the refactoring. Additionally, we implement a checkpoint mechanism to facilitate comprehensive refactoring, particularly when multiple smells are present. We evaluate UTRefactor on 879 tests from six open-source Java projects, reducing the number of test smells from 2,375 to 265, achieving an 89% reduction. UTRefactor outperforms direct LLM-based refactoring methods by 61.82% in smell elimination and significantly surpasses the performance of a rule-based test smell refactoring tool. Our results demonstrate the effectiveness of UTRefactor in enhancing test code quality while minimizing manual involvement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16739v1-abstract-full').style.display = 'none'; document.getElementById('2409.16739v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16701">arXiv:2409.16701</a> <span> [<a href="https://arxiv.org/pdf/2409.16701">pdf</a>, <a href="https://arxiv.org/format/2409.16701">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Unit Test Generation for Vulnerability Exploitation in Java Third-Party Libraries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yi Gao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xing Hu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zirui Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaohu Yang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</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="2409.16701v1-abstract-short" style="display: inline;"> Open-source third-party libraries are widely used in software development. These libraries offer substantial advantages in terms of time and resource savings. However, a significant concern arises due to the publicly disclosed vulnerabilities within these libraries. Existing automated vulnerability detection tools often suffer from false positives and fail to accurately assess the propagation of i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16701v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16701v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16701v1-abstract-full" style="display: none;"> Open-source third-party libraries are widely used in software development. These libraries offer substantial advantages in terms of time and resource savings. However, a significant concern arises due to the publicly disclosed vulnerabilities within these libraries. Existing automated vulnerability detection tools often suffer from false positives and fail to accurately assess the propagation of inputs capable of triggering vulnerabilities from client projects to vulnerable code in libraries. In this paper, we propose a novel approach called VULEUT (Vulnerability Exploit Unit Test Generation), which combines vulnerability exploitation reachability analysis and LLM-based unit test generation. VULEUT is designed to automatically verify the exploitability of vulnerabilities in third-party libraries commonly used in client software projects. VULEUT first analyzes the client projects to determine the reachability of vulnerability conditions. And then, it leverages the Large Language Model (LLM) to generate unit tests for vulnerability confirmation. To evaluate the effectiveness of VULEUT, we collect 32 vulnerabilities from various third-party libraries and conduct experiments on 70 real client projects. Besides, we also compare our approach with two representative tools, i.e., TRANSFER and VESTA. Our results demonstrate the effectiveness of VULEUT, with 229 out of 292 generated unit tests successfully confirming vulnerability exploitation across 70 client projects, which outperforms baselines by 24%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16701v1-abstract-full').style.display = 'none'; document.getElementById('2409.16701v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16656">arXiv:2409.16656</a> <span> [<a href="https://arxiv.org/pdf/2409.16656">pdf</a>, <a href="https://arxiv.org/format/2409.16656">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> A Rule-Based Approach for UI Migration from Android to iOS </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yi Gao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xing Hu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tongtong Xu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaohu 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="2409.16656v1-abstract-short" style="display: inline;"> In the mobile development process, creating the user interface (UI) is highly resource intensive. Consequently, numerous studies have focused on automating UI development, such as generating UI from screenshots or design specifications. However, they heavily rely on computer vision techniques for image recognition. Any recognition errors can cause invalid UI element generation, compromising the ef… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16656v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16656v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16656v1-abstract-full" style="display: none;"> In the mobile development process, creating the user interface (UI) is highly resource intensive. Consequently, numerous studies have focused on automating UI development, such as generating UI from screenshots or design specifications. However, they heavily rely on computer vision techniques for image recognition. Any recognition errors can cause invalid UI element generation, compromising the effectiveness of these automated approaches. Moreover, developing an app UI from scratch remains a time consuming and labor intensive task. To address this challenge, we propose a novel approach called GUIMIGRATOR, which enables the cross platform migration of existing Android app UIs to iOS, thereby automatically generating UI to facilitate the reuse of existing UI. This approach not only avoids errors from screenshot recognition but also reduces the cost of developing UIs from scratch. GUIMIGRATOR extracts and parses Android UI layouts, views, and resources to construct a UI skeleton tree. GUIMIGRATOR generates the final UI code files utilizing target code templates, which are then compiled and validated in the iOS development platform, i.e., Xcode. We evaluate the effectiveness of GUIMIGRATOR on 31 Android open source applications across ten domains. The results show that GUIMIGRATOR achieves a UI similarity score of 78 between migration screenshots, outperforming two popular existing LLMs substantially. Additionally, GUIMIGRATOR demonstrates high efficiency, taking only 7.6 seconds to migrate the datasets. These findings indicate that GUIMIGRATOR effectively facilitates the reuse of Android UI code on iOS, leveraging the strengths of both platforms UI frameworks and making new contributions to cross platform development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16656v1-abstract-full').style.display = 'none'; document.getElementById('2409.16656v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16301">arXiv:2409.16301</a> <span> [<a href="https://arxiv.org/pdf/2409.16301">pdf</a>, <a href="https://arxiv.org/format/2409.16301">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xingpeng Xia</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+J+J">Jason J. Choi</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+A">Ayush Agrawal</a>, <a href="/search/cs?searchtype=author&query=Sreenath%2C+K">Koushil Sreenath</a>, <a href="/search/cs?searchtype=author&query=Tomlin%2C+C+J">Claire J. Tomlin</a>, <a href="/search/cs?searchtype=author&query=Bansal%2C+S">Somil Bansal</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="2409.16301v1-abstract-short" style="display: inline;"> Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine their effectiveness. In this work, we are interested in designing a learning-based locomotion controller whose stability can be examined and guaranteed. This can be achieved by verifying regions of attraction (RoAs) of l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16301v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16301v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16301v1-abstract-full" style="display: none;"> Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine their effectiveness. In this work, we are interested in designing a learning-based locomotion controller whose stability can be examined and guaranteed. This can be achieved by verifying regions of attraction (RoAs) of legged robots to their stable walking gaits. This is a non-trivial problem for legged robots due to their hybrid dynamics. Although previous work has shown the utility of Hamilton-Jacobi (HJ) reachability to solve this problem, its practicality was limited by its poor scalability. The core contribution of our work is the employment of a deep learning-based HJ reachability solution to the hybrid legged robot dynamics, which overcomes the previous work's limitation. With the learned reachability solution, first, we can estimate a library of RoAs for various gaits. Second, we can design a one-step predictive controller that effectively stabilizes to an individual gait within the verified RoA. Finally, we can devise a strategy that switches gaits, in response to external perturbations, whose feasibility is guided by the RoA analysis. We demonstrate our method in a two-link walker simulation, whose mathematical model is well established. Our method achieves improved stability than previous model-based methods, while ensuring transparency that was not present in the existing learning-based approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16301v1-abstract-full').style.display = 'none'; document.getElementById('2409.16301v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">The first two authors contributed equally. This work is supported in part by the NSF Grant CMMI-1944722, the NSF CAREER Program under award 2240163, the NASA ULI on Safe Aviation Autonomy, and the DARPA Assured Autonomy and Assured Neuro Symbolic Learning and Reasoning (ANSR) programs. The work of Jason J. Choi received the support of a fellowship from Kwanjeong Educational Foundation, Korea</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16280">arXiv:2409.16280</a> <span> [<a href="https://arxiv.org/pdf/2409.16280">pdf</a>, <a href="https://arxiv.org/format/2409.16280">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"> MonoFormer: One Transformer for Both Diffusion and Autoregression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Chuyang Zhao</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Y">Yuxing Song</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wenhao Wang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+H">Haocheng Feng</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+E">Errui Ding</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yifan Sun</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xinyan Xiao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingdong 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="2409.16280v1-abstract-short" style="display: inline;"> Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16280v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16280v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16280v1-abstract-full" style="display: none;"> Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility comes from two main aspects: (i) Transformer is successfully applied to diffusion for visual generation, and (ii) transformer training for autoregression and diffusion is very similar, and the difference merely lies in that diffusion uses bidirectional attention mask and autoregression uses causal attention mask. Experimental results show that our approach achieves comparable image generation performance to current state-of-the-art methods as well as maintains the text generation capability. The project is publicly available at https://monoformer.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16280v1-abstract-full').style.display = 'none'; document.getElementById('2409.16280v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 September, 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/2409.15259">arXiv:2409.15259</a> <span> [<a href="https://arxiv.org/pdf/2409.15259">pdf</a>, <a href="https://arxiv.org/format/2409.15259">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> S$^2$AG-Vid: Enhancing Multi-Motion Alignment in Video Diffusion Models via Spatial and Syntactic Attention-Based Guidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuanhang Li</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Q">Qi Mao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lan Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zhen Fang</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+L">Lei Tian</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xinyan Xiao</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+L">Libiao Jin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hua 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="2409.15259v1-abstract-short" style="display: inline;"> Recent advancements in text-to-video (T2V) generation using diffusion models have garnered significant attention. However, existing T2V models primarily focus on simple scenes featuring a single object performing a single motion. Challenges arise in scenarios involving multiple objects with distinct motions, often leading to incorrect video-text alignment between subjects and their corresponding m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15259v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15259v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15259v1-abstract-full" style="display: none;"> Recent advancements in text-to-video (T2V) generation using diffusion models have garnered significant attention. However, existing T2V models primarily focus on simple scenes featuring a single object performing a single motion. Challenges arise in scenarios involving multiple objects with distinct motions, often leading to incorrect video-text alignment between subjects and their corresponding motions. To address this challenge, we propose \textbf{S$^2$AG-Vid}, a training-free inference-stage optimization method that improves the alignment of multiple objects with their corresponding motions in T2V models. S$^2$AG-Vid initially applies a spatial position-based, cross-attention (CA) constraint in the early stages of the denoising process, facilitating multiple nouns distinctly attending to the correct subject regions. To enhance the motion-subject binding, we implement a syntax-guided contrastive constraint in the subsequent denoising phase, aimed at improving the correlations between the CA maps of verbs and their corresponding nouns.Both qualitative and quantitative evaluations demonstrate that the proposed framework significantly outperforms baseline approaches, producing higher-quality videos with improved subject-motion consistency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15259v1-abstract-full').style.display = 'none'; document.getElementById('2409.15259v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 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/2409.14262">arXiv:2409.14262</a> <span> [<a href="https://arxiv.org/pdf/2409.14262">pdf</a>, <a href="https://arxiv.org/format/2409.14262">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"> GND: Global Navigation Dataset with Multi-Modal Perception and Multi-Category Traversability in Outdoor Campus Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+J">Jing Liang</a>, <a href="/search/cs?searchtype=author&query=Das%2C+D">Dibyendu Das</a>, <a href="/search/cs?searchtype=author&query=Song%2C+D">Daeun Song</a>, <a href="/search/cs?searchtype=author&query=Shuvo%2C+M+N+H">Md Nahid Hasan Shuvo</a>, <a href="/search/cs?searchtype=author&query=Durrani%2C+M">Mohammad Durrani</a>, <a href="/search/cs?searchtype=author&query=Taranath%2C+K">Karthik Taranath</a>, <a href="/search/cs?searchtype=author&query=Penskiy%2C+I">Ivan Penskiy</a>, <a href="/search/cs?searchtype=author&query=Manocha%2C+D">Dinesh Manocha</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.14262v2-abstract-short" style="display: inline;"> Navigating large-scale outdoor environments requires complex reasoning in terms of geometric structures, environmental semantics, and terrain characteristics, which are typically captured by onboard sensors such as LiDAR and cameras. While current mobile robots can navigate such environments using pre-defined, high-precision maps based on hand-crafted rules catered for the specific environment, th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14262v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14262v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14262v2-abstract-full" style="display: none;"> Navigating large-scale outdoor environments requires complex reasoning in terms of geometric structures, environmental semantics, and terrain characteristics, which are typically captured by onboard sensors such as LiDAR and cameras. While current mobile robots can navigate such environments using pre-defined, high-precision maps based on hand-crafted rules catered for the specific environment, they lack commonsense reasoning capabilities that most humans possess when navigating unknown outdoor spaces. To address this gap, we introduce the Global Navigation Dataset (GND), a large-scale dataset that integrates multi-modal sensory data, including 3D LiDAR point clouds and RGB and 360-degree images, as well as multi-category traversability maps (pedestrian walkways, vehicle roadways, stairs, off-road terrain, and obstacles) from ten university campuses. These environments encompass a variety of parks, urban settings, elevation changes, and campus layouts of different scales. The dataset covers approximately 2.7km2 and includes at least 350 buildings in total. We also present a set of novel applications of GND to showcase its utility to enable global robot navigation, such as map-based global navigation, mapless navigation, and global place recognition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14262v2-abstract-full').style.display = 'none'; document.getElementById('2409.14262v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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/2409.13637">arXiv:2409.13637</a> <span> [<a href="https://arxiv.org/pdf/2409.13637">pdf</a>, <a href="https://arxiv.org/format/2409.13637">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"> Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+S">Sen Lei</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xinyu Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Heng-Chao Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Zhenwei Shi</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Qing Zhu</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="2409.13637v1-abstract-short" style="display: inline;"> Given a language expression, referring remote sensing image segmentation (RRSIS) aims to identify the ground objects and assign pixel-wise labels within the imagery. The one of key challenges for this task is to capture discriminative multi-modal features via text-image alignment. However, the existing RRSIS methods use one vanilla and coarse alignment, where the language expression is directly ex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13637v1-abstract-full').style.display = 'inline'; document.getElementById('2409.13637v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13637v1-abstract-full" style="display: none;"> Given a language expression, referring remote sensing image segmentation (RRSIS) aims to identify the ground objects and assign pixel-wise labels within the imagery. The one of key challenges for this task is to capture discriminative multi-modal features via text-image alignment. However, the existing RRSIS methods use one vanilla and coarse alignment, where the language expression is directly extracted to be fused with the visual features. In this paper, we argue that a "fine-grained image-text alignment" can improve the extraction of multi-modal information. To this point, we here proposed a new referring remote sensing image segmentation method, termed FIANet, that fully exploits the visual and linguistic representations. Specifically, the original referring expression is regarded as context text, which is further decoupled into ground object text and spatial position text. The proposed fine-grained image-text alignment module (FIAM) would simultaneously leverage the features of the input image and the corresponding texts and learn better discriminative multi-modal representation. Meanwhile, to handle the various scales of ground objects in remote sensing, we introduce a Text-aware Multi-scale Enhancement Module (TMEM) to adaptively perform cross-scale fusion and intersections. We evaluate the effectiveness of the proposed methods on two public referring remote sensing datasets including RefSegRS and RRSIS-D, and our method obtains superior performance over several state-of-the-art methods. The code will be publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13637v1-abstract-full').style.display = 'none'; document.getElementById('2409.13637v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">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/2409.11570">arXiv:2409.11570</a> <span> [<a href="https://arxiv.org/pdf/2409.11570">pdf</a>, <a href="https://arxiv.org/format/2409.11570">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"> VertiEncoder: Self-Supervised Kinodynamic Representation Learning on Vertically Challenging Terrain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nazeri%2C+M">Mohammad Nazeri</a>, <a href="/search/cs?searchtype=author&query=Datar%2C+A">Aniket Datar</a>, <a href="/search/cs?searchtype=author&query=Pokhrel%2C+A">Anuj Pokhrel</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Warnell%2C+G">Garrett Warnell</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.11570v1-abstract-short" style="display: inline;"> We present VertiEncoder, a self-supervised representation learning approach for robot mobility on vertically challenging terrain. Using the same pre-training process, VertiEncoder can handle four different downstream tasks, including forward kinodynamics learning, inverse kinodynamics learning, behavior cloning, and patch reconstruction with a single representation. VertiEncoder uses a Transformer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11570v1-abstract-full').style.display = 'inline'; document.getElementById('2409.11570v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.11570v1-abstract-full" style="display: none;"> We present VertiEncoder, a self-supervised representation learning approach for robot mobility on vertically challenging terrain. Using the same pre-training process, VertiEncoder can handle four different downstream tasks, including forward kinodynamics learning, inverse kinodynamics learning, behavior cloning, and patch reconstruction with a single representation. VertiEncoder uses a TransformerEncoder to learn the local context of its surroundings by random masking and next patch reconstruction. We show that VertiEncoder achieves better performance across all four different tasks compared to specialized End-to-End models with 77% fewer parameters. We also show VertiEncoder's comparable performance against state-of-the-art kinodynamic modeling and planning approaches in real-world robot deployment. These results underscore the efficacy of VertiEncoder in mitigating overfitting and fostering more robust generalization across diverse environmental contexts and downstream vehicle kinodynamic tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11570v1-abstract-full').style.display = 'none'; document.getElementById('2409.11570v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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">8 pages. Code: https://github.com/mhnazeri/VertiEncoder</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.10280">arXiv:2409.10280</a> <span> [<a href="https://arxiv.org/pdf/2409.10280">pdf</a>, <a href="https://arxiv.org/format/2409.10280">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </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/10.1145/3691620.3695552">10.1145/3691620.3695552 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+J">Jia Feng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiachen Liu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+C">Cuiyun Gao</a>, <a href="/search/cs?searchtype=author&query=Chong%2C+C+Y">Chun Yong Chong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chaozheng Wang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shan Gao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</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="2409.10280v1-abstract-short" style="display: inline;"> In recent years, the application of large language models (LLMs) to code-related tasks has gained significant attention. However, existing evaluation benchmarks often focus on limited scenarios, such as code generation or completion, which do not reflect the diverse challenges developers face in real-world contexts. To address this, we introduce ComplexCodeEval, a benchmark designed to assess LCMs… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10280v1-abstract-full').style.display = 'inline'; document.getElementById('2409.10280v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.10280v1-abstract-full" style="display: none;"> In recent years, the application of large language models (LLMs) to code-related tasks has gained significant attention. However, existing evaluation benchmarks often focus on limited scenarios, such as code generation or completion, which do not reflect the diverse challenges developers face in real-world contexts. To address this, we introduce ComplexCodeEval, a benchmark designed to assess LCMs in various development tasks, including code generation, completion, API recommendation, and test case generation. It includes 3,897 Java samples and 7,184 Python samples from high-star GitHub repositories, each annotated with function signatures, docstrings, and API references to simulate real development environments. Our experiments across ten LCMs reveal that context improves performance and that data leakage can lead to overestimation, highlighting the need for more accurate evaluations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10280v1-abstract-full').style.display = 'none'; document.getElementById('2409.10280v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 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/2409.08692">arXiv:2409.08692</a> <span> [<a href="https://arxiv.org/pdf/2409.08692">pdf</a>, <a href="https://arxiv.org/format/2409.08692">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div 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/10.1145/3691620.3695536">10.1145/3691620.3695536 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+M">Mouxiang Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhongxin Liu</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+H">He Tao</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+Y">Yusu Hong</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+D">David Lo</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jianling Sun</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="2409.08692v1-abstract-short" style="display: inline;"> Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08692v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08692v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08692v1-abstract-full" style="display: none;"> Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy B4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios. Our code is publicly available at https://github.com/ZJU-CTAG/B4. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08692v1-abstract-full').style.display = 'none'; document.getElementById('2409.08692v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted by ASE' 24 (full paper)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08222">arXiv:2409.08222</a> <span> [<a href="https://arxiv.org/pdf/2409.08222">pdf</a>, <a href="https://arxiv.org/format/2409.08222">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Multi-Robot Coordination Induced in an Adversarial Graph-Traversal Game </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Berneburg%2C+J">James Berneburg</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xuan Wang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</a>, <a href="/search/cs?searchtype=author&query=Shishika%2C+D">Daigo Shishika</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="2409.08222v2-abstract-short" style="display: inline;"> This paper presents a game theoretic formulation of a graph traversal problem, with applications to robots moving through hazardous environments in the presence of an adversary, as in military and security scenarios. The blue team of robots moves in an environment modeled by a time-varying graph, attempting to reach some goal with minimum cost, while the red team controls how the graph changes to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08222v2-abstract-full').style.display = 'inline'; document.getElementById('2409.08222v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08222v2-abstract-full" style="display: none;"> This paper presents a game theoretic formulation of a graph traversal problem, with applications to robots moving through hazardous environments in the presence of an adversary, as in military and security scenarios. The blue team of robots moves in an environment modeled by a time-varying graph, attempting to reach some goal with minimum cost, while the red team controls how the graph changes to maximize the cost. The problem is formulated as a stochastic game, so that Nash equilibrium strategies can be computed numerically. Bounds are provided for the game value, with a guarantee that it solves the original problem. Numerical simulations demonstrate the results and the effectiveness of this method, particularly showing the benefit of mixing actions for both players, as well as beneficial coordinated behavior, where blue robots split up and/or synchronize to traverse risky edges. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08222v2-abstract-full').style.display = 'none'; document.getElementById('2409.08222v2-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">v1</span> submitted 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">8 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05840">arXiv:2409.05840</a> <span> [<a href="https://arxiv.org/pdf/2409.05840">pdf</a>, <a href="https://arxiv.org/format/2409.05840">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"> MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+R">Run Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haonan Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Longze Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Ting-En Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiong Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuchuan Wu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Min Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Minzheng Wang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+P">Pengpeng Zeng</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Lianli Gao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+H+T">Heng Tao Shen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunshui Li</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaobo Xia</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+F">Fei Huang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jingkuan Song</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yongbin 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="2409.05840v3-abstract-short" style="display: inline;"> The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs capabilities through diverse architectures, the gains have become increasingly marginal. Conversely, data-driven methods, which scale up image-text instruction… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05840v3-abstract-full').style.display = 'inline'; document.getElementById('2409.05840v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05840v3-abstract-full" style="display: none;"> The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs capabilities through diverse architectures, the gains have become increasingly marginal. Conversely, data-driven methods, which scale up image-text instruction data, are more effective but face limited data diversity and complexity challenges. The absence of high-quality data constitutes a significant development barrier for MLLMs. To address the data quality bottleneck, we propose MMEvol, a novel multimodal instruction data evolution framework. This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities. Beginning with an initial set of instructions, SEED-163K, we utilize MMEvol to systematically broaden the diversity of instruction types, extend visual reasoning steps to improve cognitive reasoning abilities, and thoroughly explore fine-grained information within images to enhance visual understanding and robustness. To comprehensively evaluate the effectiveness of our approach, we conduct extensive qualitative analysis and quantitative experiments across 13 vision-language tasks. Compared to baseline models trained with the initial seed data, the results demonstrate that our method achieves an average accuracy improvement of 3.1 percentage points. Furthermore, our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05840v3-abstract-full').style.display = 'none'; document.getElementById('2409.05840v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.03801">arXiv:2409.03801</a> <span> [<a href="https://arxiv.org/pdf/2409.03801">pdf</a>, <a href="https://arxiv.org/format/2409.03801">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yewen Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chaojie Wang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiaobo Xia</a>, <a href="/search/cs?searchtype=author&query=He%2C+X">Xu He</a>, <a href="/search/cs?searchtype=author&query=An%2C+R">Ruyi An</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Dong Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tongliang Liu</a>, <a href="/search/cs?searchtype=author&query=An%2C+B">Bo An</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinrun 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="2409.03801v1-abstract-short" style="display: inline;"> Unsupervised out-of-distribution (U-OOD) detection is to identify OOD data samples with a detector trained solely on unlabeled in-distribution (ID) data. The likelihood function estimated by a deep generative model (DGM) could be a natural detector, but its performance is limited in some popular "hard" benchmarks, such as FashionMNIST (ID) vs. MNIST (OOD). Recent studies have developed various det… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03801v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03801v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03801v1-abstract-full" style="display: none;"> Unsupervised out-of-distribution (U-OOD) detection is to identify OOD data samples with a detector trained solely on unlabeled in-distribution (ID) data. The likelihood function estimated by a deep generative model (DGM) could be a natural detector, but its performance is limited in some popular "hard" benchmarks, such as FashionMNIST (ID) vs. MNIST (OOD). Recent studies have developed various detectors based on DGMs to move beyond likelihood. However, despite their success on "hard" benchmarks, most of them struggle to consistently surpass or match the performance of likelihood on some "non-hard" cases, such as SVHN (ID) vs. CIFAR10 (OOD) where likelihood could be a nearly perfect detector. Therefore, we appeal for more attention to incremental effectiveness on likelihood, i.e., whether a method could always surpass or at least match the performance of likelihood in U-OOD detection. We first investigate the likelihood of variational DGMs and find its detection performance could be improved in two directions: i) alleviating latent distribution mismatch, and ii) calibrating the dataset entropy-mutual integration. Then, we apply two techniques for each direction, specifically post-hoc prior and dataset entropy-mutual calibration. The final method, named Resultant, combines these two directions for better incremental effectiveness compared to either technique alone. Experimental results demonstrate that the Resultant could be a new state-of-the-art U-OOD detector while maintaining incremental effectiveness on likelihood in a wide range of tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03801v1-abstract-full').style.display = 'none'; document.getElementById('2409.03801v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 September, 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/2409.03005">arXiv:2409.03005</a> <span> [<a href="https://arxiv.org/pdf/2409.03005">pdf</a>, <a href="https://arxiv.org/format/2409.03005">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cai%2C+X">Xiaoyi Cai</a>, <a href="/search/cs?searchtype=author&query=Queeney%2C+J">James Queeney</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tong Xu</a>, <a href="/search/cs?searchtype=author&query=Datar%2C+A">Aniket Datar</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Miller%2C+M">Max Miller</a>, <a href="/search/cs?searchtype=author&query=Flather%2C+A">Ashton Flather</a>, <a href="/search/cs?searchtype=author&query=Osteen%2C+P+R">Philip R. Osteen</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+N">Nicholas Roy</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</a>, <a href="/search/cs?searchtype=author&query=How%2C+J+P">Jonathan P. How</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="2409.03005v1-abstract-short" style="display: inline;"> Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03005v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03005v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03005v1-abstract-full" style="display: none;"> Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly conservative, e.g., when novel terrain can be effectively analyzed using a physics-based model. To overcome this challenge, we introduce Physics-Informed Evidential Traversability (PIETRA), a self-supervised learning framework that integrates physics priors directly into the mathematical formulation of evidential neural networks and introduces physics knowledge implicitly through an uncertainty-aware, physics-informed training loss. Our evidential network seamlessly transitions between learned and physics-based predictions for out-of-distribution inputs. Additionally, the physics-informed loss regularizes the learned model, ensuring better alignment with the physics model. Extensive simulations and hardware experiments demonstrate that PIETRA improves both learning accuracy and navigation performance in environments with significant distribution shifts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03005v1-abstract-full').style.display = 'none'; document.getElementById('2409.03005v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 September, 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">Submitted to RA-L. Video: https://youtu.be/OTnNZ96oJRk</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.02616">arXiv:2409.02616</a> <span> [<a href="https://arxiv.org/pdf/2409.02616">pdf</a>, <a href="https://arxiv.org/format/2409.02616">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Group Information Geometry Approach for Ultra-Massive MIMO Signal Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiyuan Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yan Chen</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xiqi Gao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiang-Gen Xia</a>, <a href="/search/cs?searchtype=author&query=Slock%2C+D">Dirk Slock</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="2409.02616v1-abstract-short" style="display: inline;"> We propose a group information geometry approach (GIGA) for ultra-massive multiple-input multiple-output (MIMO) signal detection. The signal detection task is framed as computing the approximate marginals of the a posteriori distribution of the transmitted data symbols of all users. With the approximate marginals, we perform the maximization of the {\textsl{a posteriori}} marginals (MPM) detection… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02616v1-abstract-full').style.display = 'inline'; document.getElementById('2409.02616v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02616v1-abstract-full" style="display: none;"> We propose a group information geometry approach (GIGA) for ultra-massive multiple-input multiple-output (MIMO) signal detection. The signal detection task is framed as computing the approximate marginals of the a posteriori distribution of the transmitted data symbols of all users. With the approximate marginals, we perform the maximization of the {\textsl{a posteriori}} marginals (MPM) detection to recover the symbol of each user. Based on the information geometry theory and the grouping of the components of the received signal, three types of manifolds are constructed and the approximate a posteriori marginals are obtained through m-projections. The Berry-Esseen theorem is introduced to offer an approximate calculation of the m-projection, while its direct calculation is exponentially complex. In most cases, more groups, less complexity of GIGA. However, when the number of groups exceeds a certain threshold, the complexity of GIGA starts to increase. Simulation results confirm that the proposed GIGA achieves better bit error rate (BER) performance within a small number of iterations, which demonstrates that it can serve as an efficient detection method in ultra-massive MIMO systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02616v1-abstract-full').style.display = 'none'; document.getElementById('2409.02616v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 September, 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/2409.02383">arXiv:2409.02383</a> <span> [<a href="https://arxiv.org/pdf/2409.02383">pdf</a>, <a href="https://arxiv.org/format/2409.02383">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"> Reinforcement Learning for Wheeled Mobility on Vertically Challenging Terrain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tong Xu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+C">Chenhui Pan</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuesu Xiao</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="2409.02383v2-abstract-short" style="display: inline;"> Off-road navigation on vertically challenging terrain, involving steep slopes and rugged boulders, presents significant challenges for wheeled robots both at the planning level to achieve smooth collision-free trajectories and at the control level to avoid rolling over or getting stuck. Considering the complex model of wheel-terrain interactions, we develop an end-to-end Reinforcement Learning (RL… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02383v2-abstract-full').style.display = 'inline'; document.getElementById('2409.02383v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02383v2-abstract-full" style="display: none;"> Off-road navigation on vertically challenging terrain, involving steep slopes and rugged boulders, presents significant challenges for wheeled robots both at the planning level to achieve smooth collision-free trajectories and at the control level to avoid rolling over or getting stuck. Considering the complex model of wheel-terrain interactions, we develop an end-to-end Reinforcement Learning (RL) system for an autonomous vehicle to learn wheeled mobility through simulated trial-and-error experiences. Using a custom-designed simulator built on the Chrono multi-physics engine, our approach leverages Proximal Policy Optimization (PPO) and a terrain difficulty curriculum to refine a policy based on a reward function to encourage progress towards the goal and penalize excessive roll and pitch angles, which circumvents the need of complex and expensive kinodynamic modeling, planning, and control. Additionally, we present experimental results in the simulator and deploy our approach on a physical Verti-4-Wheeler (V4W) platform, demonstrating that RL can equip conventional wheeled robots with previously unrealized potential of navigating vertically challenging terrain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02383v2-abstract-full').style.display = 'none'; document.getElementById('2409.02383v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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/2409.02119">arXiv:2409.02119</a> <span> [<a href="https://arxiv.org/pdf/2409.02119">pdf</a>, <a href="https://arxiv.org/format/2409.02119">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> CoRA: Optimizing Low-Rank Adaptation with Common Subspace of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xiaojun Xiao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+S">Sen Shen</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+Q">Qiming Bao</a>, <a href="/search/cs?searchtype=author&query=Rong%2C+H">Hongfei Rong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kairui Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhongsheng Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiamou Liu</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="2409.02119v1-abstract-short" style="display: inline;"> In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances efficiency and performance in fine-tuning large models by reducing the number of trainable parameters and computational costs. However, current advancements in Lo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02119v1-abstract-full').style.display = 'inline'; document.getElementById('2409.02119v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02119v1-abstract-full" style="display: none;"> In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances efficiency and performance in fine-tuning large models by reducing the number of trainable parameters and computational costs. However, current advancements in LoRA might be focused on its fine-tuning methodologies, with not as much exploration as might be expected into further compression of LoRA. Since most of LoRA's parameters might still be superfluous, this may lead to unnecessary wastage of computational resources. In this paper, we propose \textbf{CoRA}: leveraging shared knowledge to optimize LoRA training by substituting its matrix $B$ with a common subspace from large models. Our two-fold method includes (1) Freezing the substitute matrix $B$ to halve parameters while training matrix $A$ for specific tasks and (2) Using the substitute matrix $B$ as an enhanced initial state for the original matrix $B$, achieving improved results with the same parameters. Our experiments show that the first approach achieves the same efficacy as the original LoRA fine-tuning while being more efficient than halving parameters. At the same time, the second approach has some improvements compared to LoRA's original fine-tuning performance. They generally attest to the effectiveness of our work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02119v1-abstract-full').style.display = 'none'; document.getElementById('2409.02119v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 August, 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/2409.01695">arXiv:2409.01695</a> <span> [<a href="https://arxiv.org/pdf/2409.01695">pdf</a>, <a href="https://arxiv.org/format/2409.01695">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> USTC-KXDIGIT System Description for ASVspoof5 Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yihao Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Haochen Wu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+N">Nan Jiang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiang Xia</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Q">Qing Gu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yunqi Hao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+P">Pengfei Cai</a>, <a href="/search/cs?searchtype=author&query=Guan%2C+Y">Yu Guan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jialong Wang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+W">Weilin Xie</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+L">Lei Fang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+S">Sian Fang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Y">Yan Song</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+W">Wu Guo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lin Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Minqiang Xu</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="2409.01695v1-abstract-short" style="display: inline;"> This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker verification, SASV). Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. For these conditions, our system consists of a cascade of a frontend f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01695v1-abstract-full').style.display = 'inline'; document.getElementById('2409.01695v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.01695v1-abstract-full" style="display: none;"> This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker verification, SASV). Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. For these conditions, our system consists of a cascade of a frontend feature extractor and a back-end classifier. We focus on extensive embedding engineering and enhancing the generalization of the back-end classifier model. Specifically, the embedding engineering is based on hand-crafted features and speech representations from a self-supervised model, used for closed and open conditions, respectively. To detect spoof attacks under various adversarial conditions, we trained multiple systems on an augmented training set. Additionally, we used voice conversion technology to synthesize fake audio from genuine audio in the training set to enrich the synthesis algorithms. To leverage the complementary information learned by different model architectures, we employed activation ensemble and fused scores from different systems to obtain the final decision score for spoof detection. During the evaluation phase, the proposed methods achieved 0.3948 minDCF and 14.33% EER in the close condition, and 0.0750 minDCF and 2.59% EER in the open condition, demonstrating the robustness of our submitted systems under adversarial conditions. In Track 2, we continued using the CM system from Track 1 and fused it with a CNN-based ASV system. This approach achieved 0.2814 min-aDCF in the closed condition and 0.0756 min-aDCF in the open condition, showcasing superior performance in the SASV system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01695v1-abstract-full').style.display = 'none'; document.getElementById('2409.01695v1-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 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">ASVspoof5 workshop paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.16706">arXiv:2408.16706</a> <span> [<a href="https://arxiv.org/pdf/2408.16706">pdf</a>, <a href="https://arxiv.org/format/2408.16706">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Incremental Context-free Grammar Inference in Black Box Settings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+F">Feifei Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xi Xiao</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xiaoyu Sun</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chuan Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shaohua Wang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jitao Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.16706v2-abstract-short" style="display: inline;"> Black-box context-free grammar inference presents a significant challenge in many practical settings due to limited access to example programs. The state-of-the-art methods, Arvada and Treevada, employ heuristic approaches to generalize grammar rules, initiating from flat parse trees and exploring diverse generalization sequences. We have observed that these approaches suffer from low quality and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16706v2-abstract-full').style.display = 'inline'; document.getElementById('2408.16706v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16706v2-abstract-full" style="display: none;"> Black-box context-free grammar inference presents a significant challenge in many practical settings due to limited access to example programs. The state-of-the-art methods, Arvada and Treevada, employ heuristic approaches to generalize grammar rules, initiating from flat parse trees and exploring diverse generalization sequences. We have observed that these approaches suffer from low quality and readability, primarily because they process entire example strings, adding to the complexity and substantially slowing down computations. To overcome these limitations, we propose a novel method that segments example strings into smaller units and incrementally infers the grammar. Our approach, named Kedavra, has demonstrated superior grammar quality (enhanced precision and recall), faster runtime, and improved readability through empirical comparison. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16706v2-abstract-full').style.display = 'none'; document.getElementById('2408.16706v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ASE'24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12232">arXiv:2408.12232</a> <span> [<a href="https://arxiv.org/pdf/2408.12232">pdf</a>, <a href="https://arxiv.org/format/2408.12232">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"> BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hanzheng Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wei Li</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xiang-Gen Xia</a>, <a href="/search/cs?searchtype=author&query=Du%2C+Q">Qian Du</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.12232v1-abstract-short" style="display: inline;"> Hyperspectral object tracking (HOT) has exhibited potential in various applications, particularly in scenes where objects are camouflaged. Existing trackers can effectively retrieve objects via band regrouping because of the bias in existing HOT datasets, where most objects tend to have distinguishing visual appearances rather than spectral characteristics. This bias allows the tracker to directly… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12232v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12232v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12232v1-abstract-full" style="display: none;"> Hyperspectral object tracking (HOT) has exhibited potential in various applications, particularly in scenes where objects are camouflaged. Existing trackers can effectively retrieve objects via band regrouping because of the bias in existing HOT datasets, where most objects tend to have distinguishing visual appearances rather than spectral characteristics. This bias allows the tracker to directly use the visual features obtained from the false-color images generated by hyperspectral images without the need to extract spectral features. To tackle this bias, we find that the tracker should focus on the spectral information when object appearance is unreliable. Thus, we provide a new task called hyperspectral camouflaged object tracking (HCOT) and meticulously construct a large-scale HCOT dataset, termed BihoT, which consists of 41,912 hyperspectral images covering 49 video sequences. The dataset covers various artificial camouflage scenes where objects have similar appearances, diverse spectrums, and frequent occlusion, making it a very challenging dataset for HCOT. Besides, a simple but effective baseline model, named spectral prompt-based distractor-aware network (SPDAN), is proposed, comprising a spectral embedding network (SEN), a spectral prompt-based backbone network (SPBN), and a distractor-aware module (DAM). Specifically, the SEN extracts spectral-spatial features via 3-D and 2-D convolutions. Then, the SPBN fine-tunes powerful RGB trackers with spectral prompts and alleviates the insufficiency of training samples. Moreover, the DAM utilizes a novel statistic to capture the distractor caused by occlusion from objects and background. Extensive experiments demonstrate that our proposed SPDAN achieves state-of-the-art performance on the proposed BihoT and other HOT datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12232v1-abstract-full').style.display = 'none'; document.getElementById('2408.12232v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12099">arXiv:2408.12099</a> <span> [<a href="https://arxiv.org/pdf/2408.12099">pdf</a>, <a href="https://arxiv.org/format/2408.12099">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Query-Efficient Video Adversarial Attack with Stylized Logo </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+D">Duoxun Tang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuxin Cao</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xi Xiao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Derui Wang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+S">Sheng Wen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tianqing Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.12099v1-abstract-short" style="display: inline;"> Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-base… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12099v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12099v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12099v1-abstract-full" style="display: none;"> Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global color, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three steps. The first step involves building a style references set for logos, which can not only make the generated examples more natural, but also carry more target class features in the targeted attacks. Then, reinforcement learning (RL) is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbation optimization is designed to optimize perturbations to improve the fooling rate in a step-by-step manner. Sufficient experimental results indicate that, SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12099v1-abstract-full').style.display = 'none'; document.getElementById('2408.12099v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.11426">arXiv:2408.11426</a> <span> [<a href="https://arxiv.org/pdf/2408.11426">pdf</a>, <a href="https://arxiv.org/format/2408.11426">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"> AS-LIO: Spatial Overlap Guided Adaptive Sliding Window LiDAR-Inertial Odometry for Aggressive FOV Variation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tianxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xuanxuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+Z">Zongbo Liao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">You 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="2408.11426v1-abstract-short" style="display: inline;"> LiDAR-Inertial Odometry (LIO) demonstrates outstanding accuracy and stability in general low-speed and smooth motion scenarios. However, in high-speed and intense motion scenarios, such as sharp turns, two primary challenges arise: firstly, due to the limitations of IMU frequency, the error in estimating significantly non-linear motion states escalates; secondly, drastic changes in the Field of Vi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11426v1-abstract-full').style.display = 'inline'; document.getElementById('2408.11426v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11426v1-abstract-full" style="display: none;"> LiDAR-Inertial Odometry (LIO) demonstrates outstanding accuracy and stability in general low-speed and smooth motion scenarios. However, in high-speed and intense motion scenarios, such as sharp turns, two primary challenges arise: firstly, due to the limitations of IMU frequency, the error in estimating significantly non-linear motion states escalates; secondly, drastic changes in the Field of View (FOV) may diminish the spatial overlap between LiDAR frame and pointcloud map (or between frames), leading to insufficient data association and constraint degradation. To address these issues, we propose a novel Adaptive Sliding window LIO framework (AS-LIO) guided by the Spatial Overlap Degree (SOD). Initially, we assess the SOD between the LiDAR frames and the registered map, directly evaluating the adverse impact of current FOV variation on pointcloud alignment. Subsequently, we design an adaptive sliding window to manage the continuous LiDAR stream and control state updates, dynamically adjusting the update step according to the SOD. This strategy enables our odometry to adaptively adopt higher update frequency to precisely characterize trajectory during aggressive FOV variation, thus effectively reducing the non-linear error in positioning. Meanwhile, the historical constraints within the sliding window reinforce the frame-to-map data association, ensuring the robustness of state estimation. Experiments show that our AS-LIO framework can quickly perceive and respond to challenging FOV change, outperforming other state-of-the-art LIO frameworks in terms of accuracy and robustness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11426v1-abstract-full').style.display = 'none'; document.getElementById('2408.11426v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 6 figures</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Xiao%2C+X&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository