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 267 results for author: <span class="mathjax">Fang, C</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=Fang%2C+C">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="Fang, C"> </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=Fang%2C+C&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="Fang, C"> <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=Fang%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10701">arXiv:2411.10701</a> <span> [<a href="https://arxiv.org/pdf/2411.10701">pdf</a>, <a href="https://arxiv.org/format/2411.10701">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ying Yang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">De Cheng</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chaowei Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yubiao Wang</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+C">Changzhe Jiao</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Lechao Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+N">Nannan 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="2411.10701v1-abstract-short" style="display: inline;"> Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for developing a safe real-world machine learning system. Current reconstruction-based methods provide a good alternative approach by measuring the reconstruction error between the input and its corresponding generative counter… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10701v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10701v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10701v1-abstract-full" style="display: none;"> Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for developing a safe real-world machine learning system. Current reconstruction-based methods provide a good alternative approach by measuring the reconstruction error between the input and its corresponding generative counterpart in the pixel/feature space. However, such generative methods face a key dilemma: improving the reconstruction power of the generative model while keeping a compact representation of the ID data. To address this issue, we propose the diffusion-based layer-wise semantic reconstruction approach for unsupervised OOD detection. The innovation of our approach is that we leverage the diffusion model's intrinsic data reconstruction ability to distinguish ID samples from OOD samples in the latent feature space. Moreover, to set up a comprehensive and discriminative feature representation, we devise a multi-layer semantic feature extraction strategy. By distorting the extracted features with Gaussian noise and applying the diffusion model for feature reconstruction, the separation of ID and OOD samples is implemented according to the reconstruction errors. Extensive experimental results on multiple benchmarks built upon various datasets demonstrate that our method achieves state-of-the-art performance in terms of detection accuracy and speed. Code is available at <https://github.com/xbyym/DLSR>. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10701v1-abstract-full').style.display = 'none'; document.getElementById('2411.10701v1-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 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">26 pages, 23 figures, published to Neurlps2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16424">arXiv:2410.16424</a> <span> [<a href="https://arxiv.org/pdf/2410.16424">pdf</a>, <a href="https://arxiv.org/format/2410.16424">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"> Promoting cross-modal representations to improve multimodal foundation models for physiological signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Ching Fang</a>, <a href="/search/cs?searchtype=author&query=Sandino%2C+C">Christopher Sandino</a>, <a href="/search/cs?searchtype=author&query=Mahasseni%2C+B">Behrooz Mahasseni</a>, <a href="/search/cs?searchtype=author&query=Minxha%2C+J">Juri Minxha</a>, <a href="/search/cs?searchtype=author&query=Pouransari%2C+H">Hadi Pouransari</a>, <a href="/search/cs?searchtype=author&query=Azemi%2C+E">Erdrin Azemi</a>, <a href="/search/cs?searchtype=author&query=Moin%2C+A">Ali Moin</a>, <a href="/search/cs?searchtype=author&query=Zippi%2C+E">Ellen Zippi</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="2410.16424v1-abstract-short" style="display: inline;"> Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining foundation models is a promising avenue for success. However, methods for developing foundation models in healthcare are still in early exploration and it is unclea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16424v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16424v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16424v1-abstract-full" style="display: none;"> Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining foundation models is a promising avenue for success. However, methods for developing foundation models in healthcare are still in early exploration and it is unclear which pretraining strategies are most effective given the diversity of physiological signals. This is partly due to challenges in multimodal health data: obtaining data across many patients is difficult and costly, there is a lot of inter-subject variability, and modalities are often heterogeneously informative across downstream tasks. Here, we explore these challenges in the PhysioNet 2018 dataset. We use a masked autoencoding objective to pretrain a multimodal model. We show that the model learns representations that can be linearly probed for a diverse set of downstream tasks. We hypothesize that cross-modal reconstruction objectives are important for successful multimodal training, as they encourage the model to integrate information across modalities. We demonstrate that modality dropout in the input space improves performance across downstream tasks. We also find that late-fusion models pretrained with contrastive learning objectives are less effective across multiple tasks. Finally, we analyze the model's representations, showing that attention weights become more cross-modal and temporally aligned with our pretraining strategy. The learned embeddings also become more distributed in terms of the modalities encoded by each unit. Overall, our work demonstrates the utility of multimodal foundation models with health data, even across diverse physiological data sources. We further argue that explicit methods for inducing cross-modality may enhance multimodal pretraining strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16424v1-abstract-full').style.display = 'none'; document.getElementById('2410.16424v1-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">NeurIPS 2024 AIM-FM Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15631">arXiv:2410.15631</a> <span> [<a href="https://arxiv.org/pdf/2410.15631">pdf</a>, <a href="https://arxiv.org/format/2410.15631">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Security of Language Models for Code: A Systematic Literature Review </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuchen Chen</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenpeng Chen</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+Y">Yifei Ge</a>, <a href="/search/cs?searchtype=author&query=Han%2C+T">Tingxu Han</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+B">Baowen 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="2410.15631v1-abstract-short" style="display: inline;"> Language models for code (CodeLMs) have emerged as powerful tools for code-related tasks, outperforming traditional methods and standard machine learning approaches. However, these models are susceptible to security vulnerabilities, drawing increasing research attention from domains such as software engineering, artificial intelligence, and cybersecurity. Despite the growing body of research focus… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15631v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15631v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15631v1-abstract-full" style="display: none;"> Language models for code (CodeLMs) have emerged as powerful tools for code-related tasks, outperforming traditional methods and standard machine learning approaches. However, these models are susceptible to security vulnerabilities, drawing increasing research attention from domains such as software engineering, artificial intelligence, and cybersecurity. Despite the growing body of research focused on the security of CodeLMs, a comprehensive survey in this area remains absent. To address this gap, we systematically review 67 relevant papers, organizing them based on attack and defense strategies. Furthermore, we provide an overview of commonly used language models, datasets, and evaluation metrics, and highlight open-source tools and promising directions for future research in securing CodeLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15631v1-abstract-full').style.display = 'none'; document.getElementById('2410.15631v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14215">arXiv:2410.14215</a> <span> [<a href="https://arxiv.org/pdf/2410.14215">pdf</a>, <a href="https://arxiv.org/format/2410.14215">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Jamming Detection and Channel Estimation for Spatially Correlated Beamspace Massive MIMO </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Du%2C+P">Pengguang Du</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Cheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Jing%2C+Y">Yindi Jing</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chao Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhilei Zhang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yongming Huang</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="2410.14215v1-abstract-short" style="display: inline;"> In this paper, we investigate the problem of jamming detection and channel estimation during multi-user uplink beam training under random pilot jamming attacks in beamspace massive multi-input-multi-output (MIMO) systems. For jamming detection, we distinguish the signals from the jammer and the user by projecting the observation signals onto the pilot space. By using the multiple projected observa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14215v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14215v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14215v1-abstract-full" style="display: none;"> In this paper, we investigate the problem of jamming detection and channel estimation during multi-user uplink beam training under random pilot jamming attacks in beamspace massive multi-input-multi-output (MIMO) systems. For jamming detection, we distinguish the signals from the jammer and the user by projecting the observation signals onto the pilot space. By using the multiple projected observation vectors corresponding to the unused pilots, we propose a jamming detection scheme based on the locally most powerful test (LMPT) for systems with general channel conditions. Analytical expressions for the probability of detection and false alarms are derived using the second-order statistics and likelihood functions of the projected observation vectors. For the detected jammer along with users, we propose a two-step minimum mean square error (MMSE) channel estimation using the projected observation vectors. As a part of the channel estimation, we develop schemes to estimate the norm and the phase of the inner-product of the legitimate pilot vector and the random jamming pilot vector, which can be obtained using linear MMSE estimation and a bilinear form of the multiple projected observation vectors. From simulations under different system parameters, we observe that the proposed technique improves the detection probability by 32.22% compared to the baseline at medium channel correlation level, and the channel estimation achieves a mean square error of -15.93dB. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14215v1-abstract-full').style.display = 'none'; document.getElementById('2410.14215v1-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 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">13 pages, 9 figures. The paper has been submitted to an IEEE journal for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08256">arXiv:2410.08256</a> <span> [<a href="https://arxiv.org/pdf/2410.08256">pdf</a>, <a href="https://arxiv.org/format/2410.08256">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="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3666025.3699339">10.1145/3666025.3699339 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sicong Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zimu Zhou</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiaqi Tang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+K">Ke Ma</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiwen Yu</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="2410.08256v1-abstract-short" style="display: inline;"> On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08256v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08256v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08256v1-abstract-full" style="display: none;"> On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pipeline notably increases the latency over standard inference, undermining the responsiveness in time-sensitive mobile applications. This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics via selective updates of adaptation-critical layers. Although the tactic is recognized in generic on-device training, TTA's unsupervised and online context presents unique challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning. Also, AdaShadow incorporates a memory I/O-aware computation reuse scheme to further reduce latency in the reforward pass. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts. At low memory and energy costs, Adashadow provides a 2x to 3.5x speedup (ms-level) over state-of-the-art TTA methods with comparable accuracy and a 14.8% to 25.4% accuracy boost over efficient supervised methods with similar latency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08256v1-abstract-full').style.display = 'none'; document.getElementById('2410.08256v1-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 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">This paper is accepted by SenSys 2024. Copyright may be transferred without notice</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> The 22th ACM Conference on Embedded Networked Sensor Systems, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.02841">arXiv:2410.02841</a> <span> [<a href="https://arxiv.org/pdf/2410.02841">pdf</a>, <a href="https://arxiv.org/format/2410.02841">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="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Demonstration Attack against In-Context Learning for Code Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ge%2C+Y">Yifei Ge</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Lou%2C+Y">Yihang Lou</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiran Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yiming Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaofang Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhihong Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.02841v1-abstract-short" style="display: inline;"> Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific code intelligence tasks and reduce training costs, researchers reveal a new capability of LLMs: in-context learning (ICL). ICL allows LLMs to learn from a few d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02841v1-abstract-full').style.display = 'inline'; document.getElementById('2410.02841v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02841v1-abstract-full" style="display: none;"> Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific code intelligence tasks and reduce training costs, researchers reveal a new capability of LLMs: in-context learning (ICL). ICL allows LLMs to learn from a few demonstrations within a specific context, achieving impressive results without parameter updating. However, the rise of ICL introduces new security vulnerabilities in the code intelligence field. In this paper, we explore a novel security scenario based on the ICL paradigm, where attackers act as third-party ICL agencies and provide users with bad ICL content to mislead LLMs outputs in code intelligence tasks. Our study demonstrates the feasibility and risks of such a scenario, revealing how attackers can leverage malicious demonstrations to construct bad ICL content and induce LLMs to produce incorrect outputs, posing significant threats to system security. We propose a novel method to construct bad ICL content called DICE, which is composed of two stages: Demonstration Selection and Bad ICL Construction, constructing targeted bad ICL content based on the user query and transferable across different query inputs. Ultimately, our findings emphasize the critical importance of securing ICL mechanisms to protect code intelligence systems from adversarial manipulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02841v1-abstract-full').style.display = 'none'; document.getElementById('2410.02841v1-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> <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">17 pages, 5 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/2410.02825">arXiv:2410.02825</a> <span> [<a href="https://arxiv.org/pdf/2410.02825">pdf</a>, <a href="https://arxiv.org/format/2410.02825">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chenhao Fang</a>, <a href="/search/cs?searchtype=author&query=Larson%2C+D">Derek Larson</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shitong Zhu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+S">Sophie Zeng</a>, <a href="/search/cs?searchtype=author&query=Summer%2C+W">Wendy Summer</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Y">Yanqing Peng</a>, <a href="/search/cs?searchtype=author&query=Hulovatyy%2C+Y">Yuriy Hulovatyy</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+R">Rajeev Rao</a>, <a href="/search/cs?searchtype=author&query=Forgues%2C+G">Gabriel Forgues</a>, <a href="/search/cs?searchtype=author&query=Pudota%2C+A">Arya Pudota</a>, <a href="/search/cs?searchtype=author&query=Goncalves%2C+A">Alex Goncalves</a>, <a href="/search/cs?searchtype=author&query=Robert%2C+H">Herv茅 Robert</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="2410.02825v2-abstract-short" style="display: inline;"> This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model with a privacy-specific knowledge base and then augment it with a semantic RAG layer. Our evaluations demonstrate that this approach enhances the model performance (as much as doubled metrics compared to out-of-box LLM)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02825v2-abstract-full').style.display = 'inline'; document.getElementById('2410.02825v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02825v2-abstract-full" style="display: none;"> This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model with a privacy-specific knowledge base and then augment it with a semantic RAG layer. Our evaluations demonstrate that this approach enhances the model performance (as much as doubled metrics compared to out-of-box LLM) in handling privacy-related queries, by grounding responses with factual information which reduces inaccuracies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02825v2-abstract-full').style.display = 'none'; document.getElementById('2410.02825v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 September, 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/2409.20414">arXiv:2409.20414</a> <span> [<a href="https://arxiv.org/pdf/2409.20414">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> KANDU-Net:A Dual-Channel U-Net with KAN for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chenglin Fang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+K">Kaigui 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="2409.20414v1-abstract-short" style="display: inline;"> The U-Net model has consistently demonstrated strong performance in the field of medical image segmentation, with various improvements and enhancements made since its introduction. This paper presents a novel architecture that integrates KAN networks with U-Net, leveraging the powerful nonlinear representation capabilities of KAN networks alongside the established strengths of U-Net. We introduce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20414v1-abstract-full').style.display = 'inline'; document.getElementById('2409.20414v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.20414v1-abstract-full" style="display: none;"> The U-Net model has consistently demonstrated strong performance in the field of medical image segmentation, with various improvements and enhancements made since its introduction. This paper presents a novel architecture that integrates KAN networks with U-Net, leveraging the powerful nonlinear representation capabilities of KAN networks alongside the established strengths of U-Net. We introduce a KAN-convolution dual-channel structure that enables the model to more effectively capture both local and global features. We explore effective methods for fusing features extracted by KAN with those obtained through convolutional layers, utilizing an auxiliary network to facilitate this integration process. Experiments conducted across multiple datasets show that our model performs well in terms of accuracy, indicating that the KAN-convolution dual-channel approach has significant potential in medical image segmentation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20414v1-abstract-full').style.display = 'none'; document.getElementById('2409.20414v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17870">arXiv:2409.17870</a> <span> [<a href="https://arxiv.org/pdf/2409.17870">pdf</a>, <a href="https://arxiv.org/format/2409.17870">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="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+S">Shaobo Ma</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chao Fang</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+H">Haikuo Shao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhongfeng 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="2409.17870v2-abstract-short" style="display: inline;"> Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor Core support and inefficient memory management, leading to suboptimal acceleration. To address these challenges, we propose a comprehensive acceleration scheme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17870v2-abstract-full').style.display = 'inline'; document.getElementById('2409.17870v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17870v2-abstract-full" style="display: none;"> Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor Core support and inefficient memory management, leading to suboptimal acceleration. To address these challenges, we propose a comprehensive acceleration scheme for arbitrary precision LLMs. At its core, we introduce a novel bipolar-INT data format that facilitates parallel computing and supports symmetric quantization, effectively reducing data redundancy. Building on this, we implement an arbitrary precision matrix multiplication scheme that decomposes and recovers matrices at the bit level, enabling flexible precision while maximizing GPU Tensor Core utilization. Furthermore, we develop an efficient matrix preprocessing method that optimizes data layout for subsequent computations. Finally, we design a data recovery-oriented memory management system that strategically utilizes fast shared memory, significantly enhancing kernel execution speed and minimizing memory access latency. Experimental results demonstrate our approach's effectiveness, with up to 2.4\times speedup in matrix multiplication compared to NVIDIA's CUTLASS. When integrated into LLMs, we achieve up to 6.7\times inference acceleration. These improvements significantly enhance LLM inference efficiency, enabling broader and more responsive applications of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17870v2-abstract-full').style.display = 'none'; document.getElementById('2409.17870v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted by ASP-DAC 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/2409.17561">arXiv:2409.17561</a> <span> [<a href="https://arxiv.org/pdf/2409.17561">pdf</a>, <a href="https://arxiv.org/format/2409.17561">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"> TestBench: Evaluating Class-Level Test Case Generation Capability of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+Y">Ye Shang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+S">Siqi Gu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jianyi Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17561v1-abstract-short" style="display: inline;"> Software testing is a crucial phase in the software life cycle, helping identify potential risks and reduce maintenance costs. With the advancement of Large Language Models (LLMs), researchers have proposed an increasing number of LLM-based software testing techniques, particularly in the area of test case generation. Despite the growing interest, limited efforts have been made to thoroughly evalu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17561v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17561v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17561v1-abstract-full" style="display: none;"> Software testing is a crucial phase in the software life cycle, helping identify potential risks and reduce maintenance costs. With the advancement of Large Language Models (LLMs), researchers have proposed an increasing number of LLM-based software testing techniques, particularly in the area of test case generation. Despite the growing interest, limited efforts have been made to thoroughly evaluate the actual capabilities of LLMs in this task. In this paper, we introduce TestBench, a benchmark for class-level LLM-based test case generation. We construct a dataset of 108 Java programs from 9 real-world, large-scale projects on GitHub, each representing a different thematic domain. We then design three distinct types of prompts based on context descriptions, including self-contained context, full context, and simple context. Besides, we propose a fine-grained evaluation framework that considers five aspects of test cases: syntactic correctness, compilation correctness, test correctness, code coverage rate, and defect detection rate. Furthermore, we propose a heuristic algorithm to repair erroneous test cases generated by LLMs. We evaluate CodeLlama-13b, GPT-3.5, and GPT-4 on the TestBench, and our experimental results indicate that larger models demonstrate a greater ability to effectively utilize contextual information, thus generating higher-quality test cases. Smaller models may struggle with the noise introduced by the extensive information contained within the full context. However, when using the simplified version, namely the simple context, which is derived from the full context via abstract syntax tree analysis, the performance of these models improves significantly. Our analysis highlights the current progress and pinpoints future directions to further enhance the effectiveness of models by handling contextual information for test case generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17561v1-abstract-full').style.display = 'none'; document.getElementById('2409.17561v1-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">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/2409.14968">arXiv:2409.14968</a> <span> [<a href="https://arxiv.org/pdf/2409.14968">pdf</a>, <a href="https://arxiv.org/format/2409.14968">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"> Mutation-Based Deep Learning Framework Testing Method in JavaScript Environment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yinglong Zou</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+J">Juan Zhai</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiawei Liu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+T">Tao Zheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14968v1-abstract-short" style="display: inline;"> In recent years, Deep Learning (DL) applications in JavaScript environment have become increasingly popular. As the infrastructure for DL applications, JavaScript DL frameworks play a crucial role in the development and deployment. It is essential to ensure the quality of JavaScript DL frameworks. However, the bottleneck of limited computational resources in the JavaScript environment brings new c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14968v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14968v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14968v1-abstract-full" style="display: none;"> In recent years, Deep Learning (DL) applications in JavaScript environment have become increasingly popular. As the infrastructure for DL applications, JavaScript DL frameworks play a crucial role in the development and deployment. It is essential to ensure the quality of JavaScript DL frameworks. However, the bottleneck of limited computational resources in the JavaScript environment brings new challenges to framework testing. Specifically, JavaScript DL frameworks are equipped with various optimization mechanisms (e.g., cache reuse, inference acceleration) to overcome the bottleneck of limited computational resources. These optimization mechanisms are overlooked by existing methods, resulting in many bugs in JavaScript DL frameworks being missed. To address the above challenges, we propose a mutation-based JavaScript DL framework testing method named DLJSFuzzer. DLJSFuzzer designs 13 tensor mutation rules targeting the cache reuse mechanism to generate test input tensors. Besides, DLJSFuzzer designs eight model mutation rules targeting the inference acceleration mechanism to generate test input models. To evaluate the effectiveness of DLJSFuzzer, we conduct experiments on the most widely-used JavaScript DL framework, TensorFlow.js. The experimental results show that DLJSFuzzer outperforms state-of-the-art methods in both effectiveness and efficiency. DLJSFuzzer successfully detects 21 unique crashes and 126 unique NaN & Inconsistency bugs. All detected crashes have been reported to the open-source community, with 12 of them already confirmed by developers. Additionally, DLJSFuzzer has improved by over 47% in model generation efficiency and over 91% in bug detection efficiency compared to all baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14968v1-abstract-full').style.display = 'none'; document.getElementById('2409.14968v1-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/2409.14644">arXiv:2409.14644</a> <span> [<a href="https://arxiv.org/pdf/2409.14644">pdf</a>, <a href="https://arxiv.org/format/2409.14644">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> </div> </div> <p class="title is-5 mathjax"> zsLLMCode: An Effective Approach for Functional Code Embedding via LLM with Zero-Shot Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xian%2C+Z">Zixiang Xian</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Chenhui Cui</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+R">Rubing Huang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14644v1-abstract-short" style="display: inline;"> Regarding software engineering (SE) tasks, Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning, unlike pre-trained models (PTMs). However, LLMs are primarily designed for natural language output, and cannot directly produce intermediate embeddings from source code. They also face some challenges, for example, the restricted context… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14644v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14644v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14644v1-abstract-full" style="display: none;"> Regarding software engineering (SE) tasks, Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning, unlike pre-trained models (PTMs). However, LLMs are primarily designed for natural language output, and cannot directly produce intermediate embeddings from source code. They also face some challenges, for example, the restricted context length may prevent them from handling larger inputs, limiting their applicability to many SE tasks; while hallucinations may occur when LLMs are applied to complex downstream tasks. Motivated by the above facts, we propose zsLLMCode, a novel approach that generates functional code embeddings using LLMs. Our approach utilizes LLMs to convert source code into concise summaries through zero-shot learning, which is then transformed into functional code embeddings using specialized embedding models. This unsupervised approach eliminates the need for training and addresses the issue of hallucinations encountered with LLMs. To the best of our knowledge, this is the first approach that combines LLMs and embedding models to generate code embeddings. We conducted experiments to evaluate the performance of our approach. The results demonstrate the effectiveness and superiority of our approach over state-of-the-art unsupervised methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14644v1-abstract-full').style.display = 'none'; document.getElementById('2409.14644v1-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 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/2409.14260">arXiv:2409.14260</a> <span> [<a href="https://arxiv.org/pdf/2409.14260">pdf</a>, <a href="https://arxiv.org/format/2409.14260">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Perfect Gradient Inversion in Federated Learning: A New Paradigm from the Hidden Subset Sum Problem </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qiongxiu Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+L">Lixia Luo</a>, <a href="/search/cs?searchtype=author&query=Gini%2C+A">Agnese Gini</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+C">Changlong Ji</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhanhao Hu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiao Li</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chengfang Fang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jie Shi</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xiaolin Hu</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="2409.14260v1-abstract-short" style="display: inline;"> Federated Learning (FL) has emerged as a popular paradigm for collaborative learning among multiple parties. It is considered privacy-friendly because local data remains on personal devices, and only intermediate parameters -- such as gradients or model updates -- are shared. Although gradient inversion is widely viewed as a common attack method in FL, analytical research on reconstructing input t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14260v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14260v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14260v1-abstract-full" style="display: none;"> Federated Learning (FL) has emerged as a popular paradigm for collaborative learning among multiple parties. It is considered privacy-friendly because local data remains on personal devices, and only intermediate parameters -- such as gradients or model updates -- are shared. Although gradient inversion is widely viewed as a common attack method in FL, analytical research on reconstructing input training samples from shared gradients remains limited and is typically confined to constrained settings like small batch sizes. In this paper, we aim to overcome these limitations by addressing the problem from a cryptographic perspective. We mathematically formulate the input reconstruction problem using the gradient information shared in FL as the Hidden Subset Sum Problem (HSSP), an extension of the well-known NP-complete Subset Sum Problem (SSP). Leveraging this formulation allows us to achieve perfect input reconstruction, thereby mitigating issues such as dependence on label diversity and underperformance with large batch sizes that hinder existing empirical gradient inversion attacks. Moreover, our analysis provides insights into why empirical input reconstruction attacks degrade with larger batch sizes. By modeling the problem as HSSP, we demonstrate that the batch size $ B $ significantly affects attack complexity, with time complexity reaching $ \mathcal{O}(B^9) $. We further show that applying secure data aggregation techniques -- such as homomorphic encryption and secure multiparty computation -- provides a strong defense by increasing the time complexity to $ \mathcal{O}(N^9 B^9) $, where $ N $ is the number of local clients in FL. To the best of our knowledge, this is the first work to rigorously analyze privacy issues in FL by modeling them as HSSP, providing a concrete analytical foundation for further exploration and development of defense strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14260v1-abstract-full').style.display = 'none'; document.getElementById('2409.14260v1-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 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/2409.14017">arXiv:2409.14017</a> <span> [<a href="https://arxiv.org/pdf/2409.14017">pdf</a>, <a href="https://arxiv.org/format/2409.14017">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TVLSI.2024.3466224">10.1109/TVLSI.2024.3466224 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SPEED: A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chuanning Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chao Fang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiao Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhongfeng Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J">Jun Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14017v1-abstract-short" style="display: inline;"> Deploying deep neural networks (DNNs) on those resource-constrained edge platforms is hindered by their substantial computation and storage demands. Quantized multi-precision DNNs, denoted as MP-DNNs, offer a promising solution for these limitations but pose challenges for existing RISC-V processors due to complex instructions, suboptimal parallel processing, and inefficient dataflow mapping. To t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14017v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14017v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14017v1-abstract-full" style="display: none;"> Deploying deep neural networks (DNNs) on those resource-constrained edge platforms is hindered by their substantial computation and storage demands. Quantized multi-precision DNNs, denoted as MP-DNNs, offer a promising solution for these limitations but pose challenges for existing RISC-V processors due to complex instructions, suboptimal parallel processing, and inefficient dataflow mapping. To tackle the challenges mentioned above, SPEED, a scalable RISC-V vector (RVV) processor, is proposed to enable efficient MP-DNN inference, incorporating innovations in customized instructions, hardware architecture, and dataflow mapping. Firstly, some dedicated customized RISC-V instructions are introduced based on RVV extensions to reduce the instruction complexity, allowing SPEED to support processing precision ranging from 4-bit to 16-bit with minimized hardware overhead. Secondly, a parameterized multi-precision tensor unit is developed and integrated within the scalable module to enhance parallel processing capability by providing reconfigurable parallelism that matches the computation patterns of diverse MP-DNNs. Finally, a flexible mixed dataflow method is adopted to improve computational and energy efficiency according to the computing patterns of different DNN operators. The synthesis of SPEED is conducted on TSMC 28nm technology. Experimental results show that SPEED achieves a peak throughput of 737.9 GOPS and an energy efficiency of 1383.4 GOPS/W for 4-bit operators. Furthermore, SPEED exhibits superior area efficiency compared to prior RVV processors, with enhancements of 5.9$\sim$26.9$\times$ and 8.2$\sim$18.5$\times$ for 8-bit operator and best integer performance, respectively, which highlights SPEED's significant potential for efficient MP-DNN inference. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14017v1-abstract-full').style.display = 'none'; document.getElementById('2409.14017v1-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 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 work is accepted by 2024 IEEE Transactions on Very Large Scale Integration Systems (TVLSI)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.11531">arXiv:2409.11531</a> <span> [<a href="https://arxiv.org/pdf/2409.11531">pdf</a>, <a href="https://arxiv.org/format/2409.11531">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Leveraging AI-Generated Emotional Self-Voice to Nudge People towards their Ideal Selves </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C+M">Cathy Mengying Fang</a>, <a href="/search/cs?searchtype=author&query=Chua%2C+P">Phoebe Chua</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+S">Samantha Chan</a>, <a href="/search/cs?searchtype=author&query=Leong%2C+J">Joanne Leong</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+A">Andria Bao</a>, <a href="/search/cs?searchtype=author&query=Maes%2C+P">Pattie Maes</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="2409.11531v1-abstract-short" style="display: inline;"> Emotions, shaped by past experiences, significantly influence decision-making and goal pursuit. Traditional cognitive-behavioral techniques for personal development rely on mental imagery to envision ideal selves, but may be less effective for individuals who struggle with visualization. This paper introduces Emotional Self-Voice (ESV), a novel system combining emotionally expressive language mode… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11531v1-abstract-full').style.display = 'inline'; document.getElementById('2409.11531v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.11531v1-abstract-full" style="display: none;"> Emotions, shaped by past experiences, significantly influence decision-making and goal pursuit. Traditional cognitive-behavioral techniques for personal development rely on mental imagery to envision ideal selves, but may be less effective for individuals who struggle with visualization. This paper introduces Emotional Self-Voice (ESV), a novel system combining emotionally expressive language models and voice cloning technologies to render customized responses in the user's own voice. We investigate the potential of ESV to nudge individuals towards their ideal selves in a study with 60 participants. Across all three conditions (ESV, text-only, and mental imagination), we observed an increase in resilience, confidence, motivation, and goal commitment, but the ESV condition was perceived as uniquely engaging and personalized. We discuss the implications of designing generated self-voice systems as a personalized behavioral intervention for different scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11531v1-abstract-full').style.display = 'none'; document.getElementById('2409.11531v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09745">arXiv:2409.09745</a> <span> [<a href="https://arxiv.org/pdf/2409.09745">pdf</a>, <a href="https://arxiv.org/format/2409.09745">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haihan Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuanshi Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qianwen Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</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="2409.09745v1-abstract-short" style="display: inline;"> Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. However, a fundamental question -- for what kinds of high-dimensional learning problems SGD and its accelerated varian… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09745v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09745v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09745v1-abstract-full" style="display: none;"> Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. However, a fundamental question -- for what kinds of high-dimensional learning problems SGD and its accelerated variants can achieve optimality has yet to be well studied. This paper investigates SGD with two essential components in practice: exponentially decaying step size schedule and momentum. We establish the convergence upper bound for momentum accelerated SGD (ASGD) and propose concrete classes of learning problems under which SGD or ASGD achieves min-max optimal convergence rates. The characterization of the target function is based on standard power-law decays in (functional) linear regression. Our results unveil new insights for understanding the learning bias of SGD: (i) SGD is efficient in learning ``dense'' features where the corresponding weights are subject to an infinity norm constraint; (ii) SGD is efficient for easy problem without suffering from the saturation effect; (iii) momentum can accelerate the convergence rate by order when the learning problem is relatively hard. To our knowledge, this is the first work to clearly identify the optimal boundary of SGD versus ASGD for the problem under mild settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09745v1-abstract-full').style.display = 'none'; document.getElementById('2409.09745v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 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">46 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08081">arXiv:2409.08081</a> <span> [<a href="https://arxiv.org/pdf/2409.08081">pdf</a>, <a href="https://arxiv.org/format/2409.08081">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/10.1145/3691620.3695037">10.1145/3691620.3695037 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SoVAR: Building Generalizable Scenarios from Accident Reports for Autonomous Driving Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+A">An Guo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yuan Zhou</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+H">Haoxiang Tian</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yunjian Sun</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xinyu Gao</a>, <a href="/search/cs?searchtype=author&query=Luu%2C+A+T">Anh Tuan Luu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.08081v1-abstract-short" style="display: inline;"> Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08081v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08081v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08081v1-abstract-full" style="display: none;"> Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant challenges. In this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using accident reports from the National Highway Traffic Safety Administration's database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08081v1-abstract-full').style.display = 'none'; document.getElementById('2409.08081v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 39th IEEE/ACM International Conference on Automated Software Engineering (ASE '24), October 27-November 1, 2024, Sacramento, CA, USA </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.03267">arXiv:2409.03267</a> <span> [<a href="https://arxiv.org/pdf/2409.03267">pdf</a>, <a href="https://arxiv.org/format/2409.03267">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"> No Man is an Island: Towards Fully Automatic Programming by Code Search, Code Generation and Program Repair </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+Y">Ye Shang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tongke Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+S">Shengcheng Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.03267v1-abstract-short" style="display: inline;"> Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on three primary directions: (1) code search that reuses existing code snippets from external databases; (2) code generation that produces new code snippets from n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03267v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03267v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03267v1-abstract-full" style="display: none;"> Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on three primary directions: (1) code search that reuses existing code snippets from external databases; (2) code generation that produces new code snippets from natural language; and (3) program repair that refines existing code snippets by fixing detected bugs. Despite significant advancements, the effectiveness of state-of-the-art techniques is still limited, such as the usability of searched code and the correctness of generated code. Motivated by the real-world programming process, where developers usually use various external tools to aid their coding processes, such as code search engines and code testing tools, in this work, we propose \toolname{}, an automatic programming framework that leverages recent large language models (LLMs) to integrate the three research areas to address their inherent limitations. In particular, our framework first leverages different code search strategies to retrieve similar code snippets, which are then used to further guide the code generation process of LLMs. Our framework further validates the quality of generated code by compilers and test cases, and constructs repair prompts to query LLMs for generating correct patches. We conduct preliminary experiments to demonstrate the potential of our framework, \eg helping CodeLlama solve 267 programming problems with an improvement of 62.53\%. As a generic framework, \toolname{} can integrate various code search, generation, and repair tools, combining these three research areas together for the first time. More importantly, it demonstrates the potential of using traditional SE tools to enhance the usability of LLMs in automatic programming. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03267v1-abstract-full').style.display = 'none'; document.getElementById('2409.03267v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.16470">arXiv:2408.16470</a> <span> [<a href="https://arxiv.org/pdf/2408.16470">pdf</a>, <a href="https://arxiv.org/format/2408.16470">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/10.1145/3650212.3680373">10.1145/3650212.3680373 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> CooTest: An Automated Testing Approach for V2X Communication Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+A">An Guo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xinyu Gao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yuan Xiao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiakai Liu</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+X">Xiuting Ge</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</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="2408.16470v1-abstract-short" style="display: inline;"> Perceiving the complex driving environment precisely is crucial to the safe operation of autonomous vehicles. With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) collaboration has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. However, despite spectacular progress, several co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16470v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16470v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16470v1-abstract-full" style="display: none;"> Perceiving the complex driving environment precisely is crucial to the safe operation of autonomous vehicles. With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) collaboration has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. However, despite spectacular progress, several communication challenges can undermine the effectiveness of multi-vehicle cooperative perception. The low interpretability of Deep Neural Networks (DNNs) and the high complexity of communication mechanisms make conventional testing techniques inapplicable for the cooperative perception of autonomous driving systems (ADS). Besides, the existing testing techniques, depending on manual data collection and labeling, become time-consuming and prohibitively expensive. In this paper, we design and implement CooTest, the first automated testing tool of the V2X-oriented cooperative perception module. CooTest devises the V2X-specific metamorphic relation and equips communication and weather transformation operators that can reflect the impact of the various cooperative driving factors to produce transformed scenes. Furthermore, we adopt a V2X-oriented guidance strategy for the transformed scene generation process and improve testing efficiency. We experiment CooTest with multiple cooperative perception models with different fusion schemes to evaluate its performance on different tasks. The experiment results show that CooTest can effectively detect erroneous behaviors under various V2X-oriented driving conditions. Also, the results confirm that CooTest can improve detection average precision and decrease misleading cooperation errors by retraining with the generated scenes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16470v1-abstract-full').style.display = 'none'; document.getElementById('2408.16470v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA '24), September 16--20, 2024, Vienna, Austria </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14562">arXiv:2408.14562</a> <span> [<a href="https://arxiv.org/pdf/2408.14562">pdf</a>, <a href="https://arxiv.org/format/2408.14562">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"> A Survey of Camouflaged Object Detection and Beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+F">Fengyang Xiao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Sujie Hu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yuqi Shen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chengyu Fang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jinfa Huang</a>, <a href="/search/cs?searchtype=author&query=He%2C+C">Chunming He</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Longxiang Tang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Ziyun Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiu 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="2408.14562v1-abstract-short" style="display: inline;"> Camouflaged Object Detection (COD) refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings, posing a significant challenge for computer vision systems. In recent years, COD has garnered widespread attention due to its potential applications in surveillance, wildlife conservation, autonomous systems, and more. While several surveys on COD exist, they o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14562v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14562v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14562v1-abstract-full" style="display: none;"> Camouflaged Object Detection (COD) refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings, posing a significant challenge for computer vision systems. In recent years, COD has garnered widespread attention due to its potential applications in surveillance, wildlife conservation, autonomous systems, and more. While several surveys on COD exist, they often have limitations in terms of the number and scope of papers covered, particularly regarding the rapid advancements made in the field since mid-2023. To address this void, we present the most comprehensive review of COD to date, encompassing both theoretical frameworks and practical contributions to the field. This paper explores various COD methods across four domains, including both image-level and video-level solutions, from the perspectives of traditional and deep learning approaches. We thoroughly investigate the correlations between COD and other camouflaged scenario methods, thereby laying the theoretical foundation for subsequent analyses. Beyond object-level detection, we also summarize extended methods for instance-level tasks, including camouflaged instance segmentation, counting, and ranking. Additionally, we provide an overview of commonly used benchmarks and evaluation metrics in COD tasks, conducting a comprehensive evaluation of deep learning-based techniques in both image and video domains, considering both qualitative and quantitative performance. Finally, we discuss the limitations of current COD models and propose 9 promising directions for future research, focusing on addressing inherent challenges and exploring novel, meaningful technologies. For those interested, a curated list of COD-related techniques, datasets, and additional resources can be found at https://github.com/ChunmingHe/awesome-concealed-object-segmentation <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14562v1-abstract-full').style.display = 'none'; document.getElementById('2408.14562v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, 10 figures, 8 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/2408.14520">arXiv:2408.14520</a> <span>  </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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Towards Graph Prompt Learning: A Survey and Beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Long%2C+Q">Qingqing Long</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yuchen Yan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Peiyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chen Fang</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+W">Wentao Cui</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+Z">Zhiyuan Ning</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+M">Meng Xiao</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+N">Ning Cao</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+X">Xiao Luo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Lingjun Xu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+S">Shiyue Jiang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zheng Fang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chong Chen</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+X">Xian-Sheng Hua</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yuanchun Zhou</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="2408.14520v3-abstract-short" style="display: inline;"> Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability ac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14520v3-abstract-full').style.display = 'inline'; document.getElementById('2408.14520v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14520v3-abstract-full" style="display: none;"> Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability across various tasks. Graphs, as versatile data structures that capture relationships between entities, play pivotal roles in fields such as social network analysis, recommender systems, and biological graphs. Despite the success of pre-train and prompt learning paradigms in Natural Language Processing (NLP) and Computer Vision (CV), their application in graph domains remains nascent. In graph-structured data, not only do the node and edge features often have disparate distributions, but the topological structures also differ significantly. This diversity in graph data can lead to incompatible patterns or gaps between pre-training and fine-tuning on downstream graphs. We aim to bridge this gap by summarizing methods for alleviating these disparities. This includes exploring prompt design methodologies, comparing related techniques, assessing application scenarios and datasets, and identifying unresolved problems and challenges. This survey categorizes over 100 relevant works in this field, summarizing general design principles and the latest applications, including text-attributed graphs, molecules, proteins, and recommendation systems. Through this extensive review, we provide a foundational understanding of graph prompt learning, aiming to impact not only the graph mining community but also the broader Artificial General Intelligence (AGI) community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14520v3-abstract-full').style.display = 'none'; document.getElementById('2408.14520v3-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">v1</span> submitted 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">I have decided to temporarily withdraw this draft as I am in the process of making further revisions to improve its content</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12070">arXiv:2408.12070</a> <span> [<a href="https://arxiv.org/pdf/2408.12070">pdf</a>, <a href="https://arxiv.org/format/2408.12070">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"> Better Debugging: Combining Static Analysis and LLMs for Explainable Crashing Fault Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+J">Jiwei Yan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jinhao Huang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+J">Jun Yan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian 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="2408.12070v1-abstract-short" style="display: inline;"> Nowadays, many applications do not exist independently but rely on various frameworks or libraries. The frequent evolution and the complex implementation of framework APIs induce many unexpected post-release crashes. Starting from the crash stack traces, existing approaches either perform direct call graph (CG) tracing or construct datasets with similar crash-fixing records to locate buggy methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12070v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12070v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12070v1-abstract-full" style="display: none;"> Nowadays, many applications do not exist independently but rely on various frameworks or libraries. The frequent evolution and the complex implementation of framework APIs induce many unexpected post-release crashes. Starting from the crash stack traces, existing approaches either perform direct call graph (CG) tracing or construct datasets with similar crash-fixing records to locate buggy methods. However, these approaches are limited by the completeness of CG or dependent on historical fixing records. Moreover, they fail to explain the buggy candidates by revealing their relationship with the crashing point. To fill the gap, we propose an explainable crashing fault localization approach by combining static analysis and LLM techniques. Our primary insight is that understanding the semantics of exception-throwing statements in the framework code can help find and apprehend the buggy methods in the app code. Based on this idea, first, we design the exception-thrown summary (ETS) that describes the key elements related to each framework-specific exception and extract ETSs by performing static analysis. Then we make data-tracking of its key elements to identify and sort buggy candidates for the given crash. After that, we introduce LLMs to improve the explainability of the localization results. To construct effective LLM prompts, we design the candidate information summary (CIS) that describes multiple types of explanation-related contexts and then extract CISs via static analysis. We apply our approach to one typical scenario, i.e., locating Android framework-specific crashing faults, and implement a tool CrashTracker. For fault localization, it exhibited an overall MRR value of 0.91 in precision. For fault explanation, compared to the naive one produced by static analysis only, the LLM-powered explanation achieved a 67.04% improvement in users' satisfaction score. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12070v1-abstract-full').style.display = 'none'; document.getElementById('2408.12070v1-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/2408.04683">arXiv:2408.04683</a> <span> [<a href="https://arxiv.org/pdf/2408.04683">pdf</a>, <a href="https://arxiv.org/format/2408.04683">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Eliminating Backdoors in Neural Code Models via Trigger Inversion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuchen Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+Y">Yebo Feng</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yuan Xiao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+A">An Guo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+B">Baowen Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.04683v1-abstract-short" style="display: inline;"> Neural code models (NCMs) have been widely used for addressing various code understanding tasks, such as defect detection and clone detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted tri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04683v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04683v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04683v1-abstract-full" style="display: none;"> Neural code models (NCMs) have been widely used for addressing various code understanding tasks, such as defect detection and clone detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted trigger. It poses a significant security threat. For example, a backdoored defect detection model may misclassify user-submitted defective code as non-defective. If this insecure code is then integrated into critical systems, like autonomous driving systems, it could lead to life safety. However, there is an urgent need for effective defenses against backdoor attacks targeting NCMs. To address this issue, in this paper, we innovatively propose a backdoor defense technique based on trigger inversion, called EliBadCode. EliBadCode first filters the model vocabulary for trigger tokens to reduce the search space for trigger inversion, thereby enhancing the efficiency of the trigger inversion. Then, EliBadCode introduces a sample-specific trigger position identification method, which can reduce the interference of adversarial perturbations for subsequent trigger inversion, thereby producing effective inverted triggers efficiently. Subsequently, EliBadCode employs a Greedy Coordinate Gradient algorithm to optimize the inverted trigger and designs a trigger anchoring method to purify the inverted trigger. Finally, EliBadCode eliminates backdoors through model unlearning. We evaluate the effectiveness of EliBadCode in eliminating backdoor attacks against multiple NCMs used for three safety-critical code understanding tasks. The results demonstrate that EliBadCode can effectively eliminate backdoors while having minimal adverse effects on the normal functionality of the model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04683v1-abstract-full').style.display = 'none'; document.getElementById('2408.04683v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 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">Under review</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-04 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.2.3; I.2.2; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03095">arXiv:2408.03095</a> <span> [<a href="https://arxiv.org/pdf/2408.03095">pdf</a>, <a href="https://arxiv.org/format/2408.03095">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"> Improving LLM-based Unit test generation via Template-based Repair </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+S">Siqi Gu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+F">Fangyuan Tian</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jianyi Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.03095v4-abstract-short" style="display: inline;"> Unit test is crucial for detecting bugs in individual program units but consumes time and effort. The existing automated unit test generation methods are mainly based on search-based software testing (SBST) and language models to liberate developers. Recently, large language models (LLMs) have demonstrated remarkable reasoning and generation capabilities. However, several problems limit their abil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03095v4-abstract-full').style.display = 'inline'; document.getElementById('2408.03095v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03095v4-abstract-full" style="display: none;"> Unit test is crucial for detecting bugs in individual program units but consumes time and effort. The existing automated unit test generation methods are mainly based on search-based software testing (SBST) and language models to liberate developers. Recently, large language models (LLMs) have demonstrated remarkable reasoning and generation capabilities. However, several problems limit their ability to generate high-quality test cases: (1) LLMs may generate invalid test cases under insufficient context, resulting in compilation errors; (2) Lack of test and coverage feedback information may cause runtime errors and low coverage rates. (3) The repetitive suppression problem causes LLMs to get stuck into the repetition loop of self-repair or re-generation attempts. In this paper, we propose TestART, a novel unit test generation method that leverages the strengths of LLMs while overcoming the limitations mentioned. TestART improves LLM-based unit test via co-evolution of automated generation and repair iteration. TestART leverages the template-based repair technique to fix bugs in LLM-generated test cases, using prompt injection to guide the next-step automated generation and avoid repetition suppression. Furthermore, TestART extracts coverage information from the passed test cases and utilizes it as testing feedback to enhance the sufficiency of the final test case. This synergy between generation and repair elevates the quality, effectiveness, and readability of the produced test cases significantly beyond previous methods. In comparative experiments, the pass rate of TestART-generated test cases is 78.55%, which is approximately 18% higher than both the ChatGPT-4.0 model and the same ChatGPT-3.5-based method ChatUniTest. It also achieves an impressive line coverage rate of 90.96% on the focal methods that passed the test, exceeding EvoSuite by 3.4%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03095v4-abstract-full').style.display = 'none'; document.getElementById('2408.03095v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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/2407.12070">arXiv:2407.12070</a> <span> [<a href="https://arxiv.org/pdf/2407.12070">pdf</a>, <a href="https://arxiv.org/format/2407.12070">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ji%2C+Y">Yuhao Ji</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chao Fang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+S">Shaobo Ma</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+H">Haikuo Shao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhongfeng 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="2407.12070v1-abstract-short" style="display: inline;"> Transformer models have revolutionized AI tasks, but their large size hinders real-world deployment on resource-constrained and latency-critical edge devices. While binarized Transformers offer a promising solution by significantly reducing model size, existing approaches suffer from algorithm-hardware mismatches with limited co-design exploration, leading to suboptimal performance on edge devices… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12070v1-abstract-full').style.display = 'inline'; document.getElementById('2407.12070v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12070v1-abstract-full" style="display: none;"> Transformer models have revolutionized AI tasks, but their large size hinders real-world deployment on resource-constrained and latency-critical edge devices. While binarized Transformers offer a promising solution by significantly reducing model size, existing approaches suffer from algorithm-hardware mismatches with limited co-design exploration, leading to suboptimal performance on edge devices. Hence, we propose a co-design method for efficient end-to-end edge deployment of Transformers from three aspects: algorithm, hardware, and joint optimization. First, we propose BMT, a novel hardware-friendly binarized Transformer with optimized quantization methods and components, and we further enhance its model accuracy by leveraging the weighted ternary weight splitting training technique. Second, we develop a streaming processor mixed binarized Transformer accelerator, namely BAT, which is equipped with specialized units and scheduling pipelines for efficient inference of binarized Transformers. Finally, we co-optimize the algorithm and hardware through a design space exploration approach to achieve a global trade-off between accuracy, latency, and robustness for real-world deployments. Experimental results show our co-design achieves up to 2.14-49.37x throughput gains and 3.72-88.53x better energy efficiency over state-of-the-art Transformer accelerators, enabling efficient end-to-end edge deployment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12070v1-abstract-full').style.display = 'none'; document.getElementById('2407.12070v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted by ICCAD 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.09721">arXiv:2407.09721</a> <span> [<a href="https://arxiv.org/pdf/2407.09721">pdf</a>, <a href="https://arxiv.org/format/2407.09721">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Purrfect Pitch: Exploring Musical Interval Learning through Multisensory Interfaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chin%2C+S">Sam Chin</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C+M">Cathy Mengying Fang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+N">Nikhil Singh</a>, <a href="/search/cs?searchtype=author&query=Ibrahim%2C+I">Ibrahim Ibrahim</a>, <a href="/search/cs?searchtype=author&query=Paradiso%2C+J">Joe Paradiso</a>, <a href="/search/cs?searchtype=author&query=Maes%2C+P">Pattie Maes</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.09721v1-abstract-short" style="display: inline;"> We introduce Purrfect Pitch, a system consisting of a wearable haptic device and a custom-designed learning interface for musical ear training. We focus on the ability to identify musical intervals (sequences of two musical notes), which is a perceptually ambiguous task that usually requires strenuous rote training. With our system, the user would hear a sequence of two tones while simultaneously… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09721v1-abstract-full').style.display = 'inline'; document.getElementById('2407.09721v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09721v1-abstract-full" style="display: none;"> We introduce Purrfect Pitch, a system consisting of a wearable haptic device and a custom-designed learning interface for musical ear training. We focus on the ability to identify musical intervals (sequences of two musical notes), which is a perceptually ambiguous task that usually requires strenuous rote training. With our system, the user would hear a sequence of two tones while simultaneously receiving two corresponding vibrotactile stimuli on the back. Providing haptic feedback along the back makes the auditory distance between the two tones more salient, and the back-worn design is comfortable and unobtrusive. During training, the user receives multi-sensory feedback from our system and inputs their guessed interval value on our web-based learning interface. They see a green (otherwise red) screen for a correct guess with the correct interval value. Our study with 18 participants shows that our system enables novice learners to identify intervals more accurately and consistently than those who only received audio feedback, even after the haptic feedback is removed. We also share further insights on how to design a multisensory learning system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09721v1-abstract-full').style.display = 'none'; document.getElementById('2407.09721v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07959">arXiv:2407.07959</a> <span> [<a href="https://arxiv.org/pdf/2407.07959">pdf</a>, <a href="https://arxiv.org/format/2407.07959">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> </div> </div> <p class="title is-5 mathjax"> Source Code Summarization in the Era of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+Y">Yun Miao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuekang Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hongyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yi Liu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+G">Gelei Deng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.07959v1-abstract-short" style="display: inline;"> To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systemat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07959v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07959v1-abstract-full" style="display: none;"> To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLM-based code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs' model settings (including top\_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs' abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types. Finally, we unexpectedly find that CodeLlama-Instruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code implementation details and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07959v1-abstract-full').style.display = 'none'; document.getElementById('2407.07959v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Just accepted to the 47th International Conference on Software Engineering (ICSE 2025)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-04 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.2.3; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.05552">arXiv:2407.05552</a> <span> [<a href="https://arxiv.org/pdf/2407.05552">pdf</a>, <a href="https://arxiv.org/format/2407.05552">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"> Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jia Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Changlin Li</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Q">Qirui Sun</a>, <a href="/search/cs?searchtype=author&query=Ming%2C+J">Jiahui Ming</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chen Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jue Wang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+B">Bing Zeng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shuaicheng 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="2407.05552v1-abstract-short" style="display: inline;"> Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, a novel framework for few-shot style personalization of diffusion models. Ada-Adapter leverages off-the-shelf diffusion models and pre-trained image feature encoders to learn a com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05552v1-abstract-full').style.display = 'inline'; document.getElementById('2407.05552v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05552v1-abstract-full" style="display: none;"> Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, a novel framework for few-shot style personalization of diffusion models. Ada-Adapter leverages off-the-shelf diffusion models and pre-trained image feature encoders to learn a compact style representation from a limited set of source images. Our method enables efficient zero-shot style transfer utilizing a single reference image. Furthermore, with a small number of source images (three to five are sufficient) and a few minutes of fine-tuning, our method can capture intricate style details and conceptual characteristics, generating high-fidelity stylized images that align well with the provided text prompts. We demonstrate the effectiveness of our approach on various artistic styles, including flat art, 3D rendering, and logo design. Our experimental results show that Ada-Adapter outperforms existing zero-shot and few-shot stylization methods in terms of output quality, diversity, and training efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05552v1-abstract-full').style.display = 'none'; document.getElementById('2407.05552v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 11 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04923">arXiv:2407.04923</a> <span> [<a href="https://arxiv.org/pdf/2407.04923">pdf</a>, <a href="https://arxiv.org/format/2407.04923">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Tiancheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qianqian Zhang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+K">Kyusong Lee</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+P">Peng Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lu Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunxin Fang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+J">Jiajia Liao</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+K">Kelei Jiang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yibo Ma</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+R">Ruochen 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="2407.04923v1-abstract-short" style="display: inline;"> We introduce OmChat, a model designed to excel in handling long contexts and video understanding tasks. OmChat's new architecture standardizes how different visual inputs are processed, making it more efficient and adaptable. It uses a dynamic vision encoding process to effectively handle images of various resolutions, capturing fine details across a range of image qualities. OmChat utilizes an ac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04923v1-abstract-full').style.display = 'inline'; document.getElementById('2407.04923v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04923v1-abstract-full" style="display: none;"> We introduce OmChat, a model designed to excel in handling long contexts and video understanding tasks. OmChat's new architecture standardizes how different visual inputs are processed, making it more efficient and adaptable. It uses a dynamic vision encoding process to effectively handle images of various resolutions, capturing fine details across a range of image qualities. OmChat utilizes an active progressive multimodal pretraining strategy, which gradually increases the model's capacity for long contexts and enhances its overall abilities. By selecting high-quality data during training, OmChat learns from the most relevant and informative data points. With support for a context length of up to 512K, OmChat demonstrates promising performance in tasks involving multiple images and videos, outperforming most open-source models in these benchmarks. Additionally, OmChat proposes a prompting strategy for unifying complex multimodal inputs including single image text, multi-image text and videos, and achieving competitive performance on single-image benchmarks. To further evaluate the model's capabilities, we proposed a benchmark dataset named Temporal Visual Needle in a Haystack. This dataset assesses OmChat's ability to comprehend temporal visual details within long videos. Our analysis highlights several key factors contributing to OmChat's success: support for any-aspect high image resolution, the active progressive pretraining strategy, and high-quality supervised fine-tuning datasets. This report provides a detailed overview of OmChat's capabilities and the strategies that enhance its performance in visual understanding. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04923v1-abstract-full').style.display = 'none'; document.getElementById('2407.04923v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.01646">arXiv:2407.01646</a> <span> [<a href="https://arxiv.org/pdf/2407.01646">pdf</a>, <a href="https://arxiv.org/format/2407.01646">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> </div> </div> <p class="title is-5 mathjax"> ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuchen Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Z">Zhao Wei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=You%2C+Y">Yudu You</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+B">Bin Luo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.01646v1-abstract-short" style="display: inline;"> (Source) code summarization aims to automatically generate succinct natural language summaries for given code snippets. Such summaries play a significant role in promoting developers to understand and maintain code. Inspired by neural machine translation, deep learning-based code summarization techniques widely adopt an encoder-decoder framework, where the encoder transforms given code snippets in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.01646v1-abstract-full').style.display = 'inline'; document.getElementById('2407.01646v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.01646v1-abstract-full" style="display: none;"> (Source) code summarization aims to automatically generate succinct natural language summaries for given code snippets. Such summaries play a significant role in promoting developers to understand and maintain code. Inspired by neural machine translation, deep learning-based code summarization techniques widely adopt an encoder-decoder framework, where the encoder transforms given code snippets into context vectors, and the decoder decodes context vectors into summaries. Recently, large-scale pre-trained models for source code are equipped with encoders capable of producing general context vectors and have achieved substantial improvements on code summarization. However, although they are usually trained mainly on code-focused tasks and can capture general code features, they still fall short in capturing specific features that need to be summarized. This paper proposes a novel approach to improve code summarization based on summary-focused tasks. Specifically, we exploit a multi-task learning paradigm to train the encoder on three summary-focused tasks to enhance its ability to learn code-summary alignment, including unidirectional language modeling (ULM), masked language modeling (MLM), and action word prediction (AWP). Unlike pre-trained models that mainly predict masked tokens in code snippets, we design ULM and MLM to predict masked words in summaries. Intuitively, predicting words based on given code snippets would help learn the code-summary alignment. Additionally, we introduce the domain-specific task AWP to enhance the ability of the encoder to learn the alignment between action words and code snippets. The extensive experiments on four datasets demonstrate that our approach, called ESALE significantly outperforms baselines in all three widely used metrics, including BLEU, METEOR, and ROUGE-L. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.01646v1-abstract-full').style.display = 'none'; document.getElementById('2407.01646v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE Transactions on Software Engineering (TSE)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-04 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.2.3; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19283">arXiv:2406.19283</a> <span> [<a href="https://arxiv.org/pdf/2406.19283">pdf</a>, <a href="https://arxiv.org/format/2406.19283">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> PhysioLLM: Supporting Personalized Health Insights with Wearables and Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C+M">Cathy Mengying Fang</a>, <a href="/search/cs?searchtype=author&query=Danry%2C+V">Valdemar Danry</a>, <a href="/search/cs?searchtype=author&query=Whitmore%2C+N">Nathan Whitmore</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+A">Andria Bao</a>, <a href="/search/cs?searchtype=author&query=Hutchison%2C+A">Andrew Hutchison</a>, <a href="/search/cs?searchtype=author&query=Pierce%2C+C">Cayden Pierce</a>, <a href="/search/cs?searchtype=author&query=Maes%2C+P">Pattie Maes</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.19283v1-abstract-short" style="display: inline;"> We present PhysioLLM, an interactive system that leverages large language models (LLMs) to provide personalized health understanding and exploration by integrating physiological data from wearables with contextual information. Unlike commercial health apps for wearables, our system offers a comprehensive statistical analysis component that discovers correlations and trends in user data, allowing u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19283v1-abstract-full').style.display = 'inline'; document.getElementById('2406.19283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19283v1-abstract-full" style="display: none;"> We present PhysioLLM, an interactive system that leverages large language models (LLMs) to provide personalized health understanding and exploration by integrating physiological data from wearables with contextual information. Unlike commercial health apps for wearables, our system offers a comprehensive statistical analysis component that discovers correlations and trends in user data, allowing users to ask questions in natural language and receive generated personalized insights, and guides them to develop actionable goals. As a case study, we focus on improving sleep quality, given its measurability through physiological data and its importance to general well-being. Through a user study with 24 Fitbit watch users, we demonstrate that PhysioLLM outperforms both the Fitbit App alone and a generic LLM chatbot in facilitating a deeper, personalized understanding of health data and supporting actionable steps toward personal health goals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19283v1-abstract-full').style.display = 'none'; document.getElementById('2406.19283v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11920">arXiv:2406.11920</a> <span> [<a href="https://arxiv.org/pdf/2406.11920">pdf</a>, <a href="https://arxiv.org/format/2406.11920">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xi Chen</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+C">Chuan Qin</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chuyu Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chao Wang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+C">Chen Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+F">Fuzhen Zhuang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Hengshu Zhu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+H">Hui Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.11920v2-abstract-short" style="display: inline;"> In a rapidly evolving job market, skill demand forecasting is crucial as it enables policymakers and businesses to anticipate and adapt to changes, ensuring that workforce skills align with market needs, thereby enhancing productivity and competitiveness. Additionally, by identifying emerging skill requirements, it directs individuals towards relevant training and education opportunities, promotin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11920v2-abstract-full').style.display = 'inline'; document.getElementById('2406.11920v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11920v2-abstract-full" style="display: none;"> In a rapidly evolving job market, skill demand forecasting is crucial as it enables policymakers and businesses to anticipate and adapt to changes, ensuring that workforce skills align with market needs, thereby enhancing productivity and competitiveness. Additionally, by identifying emerging skill requirements, it directs individuals towards relevant training and education opportunities, promoting continuous self-learning and development. However, the absence of comprehensive datasets presents a significant challenge, impeding research and the advancement of this field. To bridge this gap, we present Job-SDF, a dataset designed to train and benchmark job-skill demand forecasting models. Based on 10.35 million public job advertisements collected from major online recruitment platforms in China between 2021 and 2023, this dataset encompasses monthly recruitment demand for 2,324 types of skills across 521 companies. Our dataset uniquely enables evaluating skill demand forecasting models at various granularities, including occupation, company, and regional levels. We benchmark a range of models on this dataset, evaluating their performance in standard scenarios, in predictions focused on lower value ranges, and in the presence of structural breaks, providing new insights for further research. Our code and dataset are publicly accessible via the https://github.com/Job-SDF/benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11920v2-abstract-full').style.display = 'none'; document.getElementById('2406.11920v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11249">arXiv:2406.11249</a> <span> [<a href="https://arxiv.org/pdf/2406.11249">pdf</a>, <a href="https://arxiv.org/format/2406.11249">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yang Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zhouchen Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bing 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="2406.11249v1-abstract-short" style="display: inline;"> Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical learning, particularly for prediction problems, may overlook the rich and inherently structured information from the data, especially regarding the relationships betw… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11249v1-abstract-full').style.display = 'inline'; document.getElementById('2406.11249v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11249v1-abstract-full" style="display: none;"> Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical learning, particularly for prediction problems, may overlook the rich and inherently structured information from the data, especially regarding the relationships between objects. We introduce a mathematical model that formalizes relational learning as hypergraph recovery to study pre-training of FMs. In our framework, the world is represented as a hypergraph, with data abstracted as random samples from hyperedges. We theoretically examine the feasibility of a Pre-Trained Model (PTM) to recover this hypergraph and analyze the data efficiency in a minimax near-optimal style. By integrating rich graph theories into the realm of PTMs, our mathematical framework offers powerful tools for an in-depth understanding of pre-training from a unique perspective and can be used under various scenarios. As an example, we extend the framework to entity alignment in multimodal learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11249v1-abstract-full').style.display = 'none'; document.getElementById('2406.11249v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11138">arXiv:2406.11138</a> <span> [<a href="https://arxiv.org/pdf/2406.11138">pdf</a>, <a href="https://arxiv.org/format/2406.11138">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"> Diffusion Models in Low-Level Vision: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+C">Chunming He</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yuqi Shen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chengyu Fang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+F">Fengyang Xiao</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Longxiang Tang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yulun Zhang</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+W">Wangmeng Zuo</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Zhenhua Guo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiu 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="2406.11138v1-abstract-short" style="display: inline;"> Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. This ensures the generation of visually compellin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11138v1-abstract-full').style.display = 'inline'; document.getElementById('2406.11138v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11138v1-abstract-full" style="display: none;"> Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. This ensures the generation of visually compelling results with intricate texture information. Despite their remarkable success, a noticeable gap exists in a comprehensive survey that amalgamates these pioneering diffusion model-based works and organizes the corresponding threads. This paper proposes the comprehensive review of diffusion model-based techniques. We present three generic diffusion modeling frameworks and explore their correlations with other deep generative models, establishing the theoretical foundation. Following this, we introduce a multi-perspective categorization of diffusion models, considering both the underlying framework and the target task. Additionally, we summarize extended diffusion models applied in other tasks, including medical, remote sensing, and video scenarios. Moreover, we provide an overview of commonly used benchmarks and evaluation metrics. We conduct a thorough evaluation, encompassing both performance and efficiency, of diffusion model-based techniques in three prominent tasks. Finally, we elucidate the limitations of current diffusion models and propose seven intriguing directions for future research. This comprehensive examination aims to facilitate a profound understanding of the landscape surrounding denoising diffusion models in the context of low-level vision tasks. A curated list of diffusion model-based techniques in over 20 low-level vision tasks can be found at https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11138v1-abstract-full').style.display = 'none'; document.getElementById('2406.11138v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 23 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.08340">arXiv:2406.08340</a> <span> [<a href="https://arxiv.org/pdf/2406.08340">pdf</a>, <a href="https://arxiv.org/format/2406.08340">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/10.1109/TSE.2024.3414672">10.1109/TSE.2024.3414672 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Practical, Automated Scenario-based Mobile App Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+S">Shengcheng Yu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Du%2C+M">Mingzhe Du</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Zimin Ding</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Z">Zhendong 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="2406.08340v1-abstract-short" style="display: inline;"> The importance of mobile application (app) quality insurance is increasing with the rapid development of the mobile Internet. Automated test generation approaches, as a dominant direction of app quality insurance, follow specific models or strategies, targeting at optimizing the code coverage. Such approaches lead to a huge gap between testing execution and app business logic. Test scripts develop… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08340v1-abstract-full').style.display = 'inline'; document.getElementById('2406.08340v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.08340v1-abstract-full" style="display: none;"> The importance of mobile application (app) quality insurance is increasing with the rapid development of the mobile Internet. Automated test generation approaches, as a dominant direction of app quality insurance, follow specific models or strategies, targeting at optimizing the code coverage. Such approaches lead to a huge gap between testing execution and app business logic. Test scripts developed by human testers consider business logic by focusing on testing scenarios. Due to the GUI-intensive feature of mobile apps, human testers always understand app GUI to organize test scripts for scenarios. This inspires us to utilize domain knowledge from app GUI understanding for scenario-based test generation. In this paper, we propose a novel approach, ScenTest, for scenario-based mobile app testing with event knowledge graph (EKG) via GUI image understanding. ScenTest tries to start automated testing by imitating human practices and integrating domain knowledge into scenario-based mobile app testing, realizing fully automated testing on target testing scenarios for the first time. ScenTest extracts four kinds of entities and five kinds of corresponding relationships from crowdsourced test reports, where the test events and app GUI information are presented, and constructs the EKGs for specific scenarios. Then, ScenTest conducts test generation for specific scenarios on different apps with the guidance of EKG with the combination consideration of app current state and testing context. We conduct an evaluation on ScenTest on different aspects. The results show that the test generation of ScenTest on the basis of EKG is effective, and ScenTest can reveal 80+ distinct real-world bugs in specific scenarios compared with representative baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08340v1-abstract-full').style.display = 'none'; document.getElementById('2406.08340v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Transaction on Software Engineering in 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/2406.07966">arXiv:2406.07966</a> <span> [<a href="https://arxiv.org/pdf/2406.07966">pdf</a>, <a href="https://arxiv.org/format/2406.07966">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"> Real-world Image Dehazing with Coherence-based Label Generator and Cooperative Unfolding Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chengyu Fang</a>, <a href="/search/cs?searchtype=author&query=He%2C+C">Chunming He</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+F">Fengyang Xiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yulun Zhang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Longxiang Tang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuelin Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+K">Kai Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiu 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="2406.07966v3-abstract-short" style="display: inline;"> Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07966v3-abstract-full').style.display = 'inline'; document.getElementById('2406.07966v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07966v3-abstract-full" style="display: none;"> Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at \url{https://github.com/cnyvfang/CORUN-Colabator}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07966v3-abstract-full').style.display = 'none'; document.getElementById('2406.07966v3-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 12 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 8 figures, 13 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/2406.03508">arXiv:2406.03508</a> <span> [<a href="https://arxiv.org/pdf/2406.03508">pdf</a>, <a href="https://arxiv.org/format/2406.03508">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+T">Tingxu Han</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Ziqi Ding</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+H">Hanwei Qian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaxun Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiangyu 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="2406.03508v2-abstract-short" style="display: inline;"> Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained encoders by SSL, however, are vulnerable to backdoor attacks as demonstrated by existing studies. Numerous backdoor mitigation techniques are designed for down… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03508v2-abstract-full').style.display = 'inline'; document.getElementById('2406.03508v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03508v2-abstract-full" style="display: none;"> Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained encoders by SSL, however, are vulnerable to backdoor attacks as demonstrated by existing studies. Numerous backdoor mitigation techniques are designed for downstream task models. However, their effectiveness is impaired and limited when adapted to pre-trained encoders, due to the lack of label information when pre-training. To address backdoor attacks against pre-trained encoders, in this paper, we innovatively propose a mutual information guided backdoor mitigation technique, named MIMIC. MIMIC treats the potentially backdoored encoder as the teacher net and employs knowledge distillation to distill a clean student encoder from the teacher net. Different from existing knowledge distillation approaches, MIMIC initializes the student with random weights, inheriting no backdoors from teacher nets. Then MIMIC leverages mutual information between each layer and extracted features to locate where benign knowledge lies in the teacher net, with which distillation is deployed to clone clean features from teacher to student. We craft the distillation loss with two aspects, including clone loss and attention loss, aiming to mitigate backdoors and maintain encoder performance at the same time. Our evaluation conducted on two backdoor attacks in SSL demonstrates that MIMIC can significantly reduce the attack success rate by only utilizing <5% of clean data, surpassing seven state-of-the-art backdoor mitigation techniques. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03508v2-abstract-full').style.display = 'none'; document.getElementById('2406.03508v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.03006">arXiv:2406.03006</a> <span> [<a href="https://arxiv.org/pdf/2406.03006">pdf</a>, <a href="https://arxiv.org/ps/2406.03006">ps</a>, <a href="https://arxiv.org/format/2406.03006">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Quantum Algorithms and Lower Bounds for Finite-Sum Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yexin Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liwei Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tongyang 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="2406.03006v1-abstract-short" style="display: inline;"> Finite-sum optimization has wide applications in machine learning, covering important problems such as support vector machines, regression, etc. In this paper, we initiate the study of solving finite-sum optimization problems by quantum computing. Specifically, let $f_1,\ldots,f_n\colon\mathbb{R}^d\to\mathbb{R}$ be $\ell$-smooth convex functions and $蠄\colon\mathbb{R}^d\to\mathbb{R}$ be a $渭$-stro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03006v1-abstract-full').style.display = 'inline'; document.getElementById('2406.03006v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03006v1-abstract-full" style="display: none;"> Finite-sum optimization has wide applications in machine learning, covering important problems such as support vector machines, regression, etc. In this paper, we initiate the study of solving finite-sum optimization problems by quantum computing. Specifically, let $f_1,\ldots,f_n\colon\mathbb{R}^d\to\mathbb{R}$ be $\ell$-smooth convex functions and $蠄\colon\mathbb{R}^d\to\mathbb{R}$ be a $渭$-strongly convex proximal function. The goal is to find an $蔚$-optimal point for $F(\mathbf{x})=\frac{1}{n}\sum_{i=1}^n f_i(\mathbf{x})+蠄(\mathbf{x})$. We give a quantum algorithm with complexity $\tilde{O}\big(n+\sqrt{d}+\sqrt{\ell/渭}\big(n^{1/3}d^{1/3}+n^{-2/3}d^{5/6}\big)\big)$, improving the classical tight bound $\tilde螛\big(n+\sqrt{n\ell/渭}\big)$. We also prove a quantum lower bound $\tilde惟(n+n^{3/4}(\ell/渭)^{1/4})$ when $d$ is large enough. Both our quantum upper and lower bounds can extend to the cases where $蠄$ is not necessarily strongly convex, or each $f_i$ is Lipschitz but not necessarily smooth. In addition, when $F$ is nonconvex, our quantum algorithm can find an $蔚$-critial point using $\tilde{O}(n+\ell(d^{1/3}n^{1/3}+\sqrt{d})/蔚^2)$ queries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03006v1-abstract-full').style.display = 'none'; document.getElementById('2406.03006v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">27 pages. To appear in the Forty-first International Conference on Machine Learning International Conference on Machine Learning (ICML 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/2406.01467">arXiv:2406.01467</a> <span> [<a href="https://arxiv.org/pdf/2406.01467">pdf</a>, <a href="https://arxiv.org/format/2406.01467">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> RaDe-GS: Rasterizing Depth in Gaussian Splatting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chuan Fang</a>, <a href="/search/cs?searchtype=author&query=Shrestha%2C+R">Rakesh Shrestha</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yixun Liang</a>, <a href="/search/cs?searchtype=author&query=Long%2C+X">Xiaoxiao Long</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+P">Ping Tan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.01467v2-abstract-short" style="display: inline;"> Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian splats, which complicates the shape extraction. While recent tech… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01467v2-abstract-full').style.display = 'inline'; document.getElementById('2406.01467v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.01467v2-abstract-full" style="display: none;"> Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian splats, which complicates the shape extraction. While recent techniques like 2D GS have attempted to improve shape reconstruction, they often reformulate the Gaussian primitives in ways that reduce both rendering quality and computational efficiency. To address these problems, our work introduces a rasterized approach to render the depth maps and surface normal maps of general 3D Gaussian splats. Our method not only significantly enhances shape reconstruction accuracy but also maintains the computational efficiency intrinsic to Gaussian Splatting. It achieves a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods. Our method is a significant advancement in Gaussian Splatting and can be directly integrated into existing Gaussian Splatting-based methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01467v2-abstract-full').style.display = 'none'; document.getElementById('2406.01467v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.00699">arXiv:2406.00699</a> <span> [<a href="https://arxiv.org/pdf/2406.00699">pdf</a>, <a href="https://arxiv.org/format/2406.00699">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"> Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yuan Xiao</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+S">Shiqing Ma</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+J">Juan Zhai</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+J">Jinyuan Jia</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.00699v1-abstract-short" style="display: inline;"> The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some pre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00699v1-abstract-full').style.display = 'inline'; document.getElementById('2406.00699v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00699v1-abstract-full" style="display: none;"> The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some precision to enhance efficiency and scalability, and thus, a certified lower bound is a crucial criterion for evaluating the performance of verification tools. In this paper, we present MaxLin, a robustness verifier for MaxPool-based CNNs with tight linear approximation. By tightening the linear approximation of the MaxPool function, we can certify larger certified lower bounds of CNNs. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets. The results show that MaxLin outperforms state-of-the-art tools with up to 110.60% improvement regarding the certified lower bound and 5.13 $\times$ speedup for the same neural networks. Our code is available at https://github.com/xiaoyuanpigo/maxlin. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00699v1-abstract-full').style.display = 'none'; document.getElementById('2406.00699v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to CVPR2024. Project page: https://github.com/xiaoyuanpigo/maxlin</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16886">arXiv:2405.16886</a> <span> [<a href="https://arxiv.org/pdf/2405.16886">pdf</a>, <a href="https://arxiv.org/format/2405.16886">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"> Hawk: Learning to Understand Open-World Video Anomalies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiaqi Tang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Hao Lu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+R">Ruizheng Wu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiaogang Xu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+K">Ke Ma</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiangbo Lu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qifeng Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Ying-Cong Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.16886v1-abstract-short" style="display: inline;"> Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16886v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16886v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16886v1-abstract-full" style="display: none;"> Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (VLM) to interpret video anomalies precisely. Recognizing the difference in motion information between abnormal and normal videos, Hawk explicitly integrates motion modality to enhance anomaly identification. To reinforce motion attention, we construct an auxiliary consistency loss within the motion and video space, guiding the video branch to focus on the motion modality. Moreover, to improve the interpretation of motion-to-language, we establish a clear supervisory relationship between motion and its linguistic representation. Furthermore, we have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions. The final results demonstrate that Hawk achieves SOTA performance, surpassing existing baselines in both video description generation and question-answering. Our codes/dataset/demo will be released at https://github.com/jqtangust/hawk. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16886v1-abstract-full').style.display = 'none'; document.getElementById('2405.16886v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16455">arXiv:2405.16455</a> <span> [<a href="https://arxiv.org/pdf/2405.16455">pdf</a>, <a href="https://arxiv.org/format/2405.16455">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Jiancong Xiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Ziniu Li</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+X">Xingyu Xie</a>, <a href="/search/cs?searchtype=author&query=Getzen%2C+E">Emily Getzen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</a>, <a href="/search/cs?searchtype=author&query=Long%2C+Q">Qi Long</a>, <a href="/search/cs?searchtype=author&query=Su%2C+W+J">Weijie J. 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="2405.16455v1-abstract-short" style="display: inline;"> Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that reinforcement learning from human feedback (RLHF) -- the predominant approach for aligning LLMs with human preferences through a reward model -- suffers from an inherent algorithmic bias due to its K… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16455v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16455v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16455v1-abstract-full" style="display: none;"> Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that reinforcement learning from human feedback (RLHF) -- the predominant approach for aligning LLMs with human preferences through a reward model -- suffers from an inherent algorithmic bias due to its Kullback--Leibler-based regularization in optimization. In extreme cases, this bias could lead to a phenomenon we term preference collapse, where minority preferences are virtually disregarded. To mitigate this algorithmic bias, we introduce preference matching (PM) RLHF, a novel approach that provably aligns LLMs with the preference distribution of the reward model under the Bradley--Terry--Luce/Plackett--Luce model. Central to our approach is a PM regularizer that takes the form of the negative logarithm of the LLM's policy probability distribution over responses, which helps the LLM balance response diversification and reward maximization. Notably, we obtain this regularizer by solving an ordinary differential equation that is necessary for the PM property. For practical implementation, we introduce a conditional variant of PM RLHF that is tailored to natural language generation. Finally, we empirically validate the effectiveness of conditional PM RLHF through experiments on the OPT-1.3B and Llama-2-7B models, demonstrating a 29% to 41% improvement in alignment with human preferences, as measured by a certain metric, compared to standard RLHF. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16455v1-abstract-full').style.display = 'none'; document.getElementById('2405.16455v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.05540">arXiv:2405.05540</a> <span> [<a href="https://arxiv.org/pdf/2405.05540">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/68.736393">10.1109/68.736393 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Shape-Optimized Electrooptic Beam Scanners: Experiment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+J+C">Jennifer C. Fang</a>, <a href="/search/cs?searchtype=author&query=Kawas%2C+M+J">M. J. Kawas</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+J">J. Zou</a>, <a href="/search/cs?searchtype=author&query=Gopalan%2C+V">V. Gopalan</a>, <a href="/search/cs?searchtype=author&query=Schlesinger%2C+T+E">T. E. Schlesinger</a>, <a href="/search/cs?searchtype=author&query=Stancil%2C+D+D">Daniel D. Stancil</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.05540v1-abstract-short" style="display: inline;"> A new horn-shaped electrooptic scanner is described with significantly improved scanning sensitivity over rectangular-shaped devices. In the new device, the shape of the scanner is chosen to follow the trajectory of the beam. An example design is described that exhibits a factor of two larger scanning sensitivity than a rectangular device with comparable maximum scanning angle. Beam propagation si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05540v1-abstract-full').style.display = 'inline'; document.getElementById('2405.05540v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.05540v1-abstract-full" style="display: none;"> A new horn-shaped electrooptic scanner is described with significantly improved scanning sensitivity over rectangular-shaped devices. In the new device, the shape of the scanner is chosen to follow the trajectory of the beam. An example design is described that exhibits a factor of two larger scanning sensitivity than a rectangular device with comparable maximum scanning angle. Beam propagation simulations and measurements on an experimental device verify the scanner performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05540v1-abstract-full').style.display = 'none'; document.getElementById('2405.05540v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">3 pages, 3 figures. IEEE Photonics Technology Letters. Author Jennifer C. Fang is currently known as Jennifer Andreoli-Fang</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Photonics Technology Letters ( Volume: 11, Issue: 1, January 1999) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.04715">arXiv:2405.04715</a> <span> [<a href="https://arxiv.org/pdf/2405.04715">pdf</a>, <a href="https://arxiv.org/format/2405.04715">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yihong Gu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</a>, <a href="/search/cs?searchtype=author&query=B%C3%BChlmann%2C+P">Peter B眉hlmann</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+J">Jianqing Fan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.04715v2-abstract-short" style="display: inline;"> Pursuing causality from data is a fundamental problem in scientific discovery, treatment intervention, and transfer learning. This paper introduces a novel algorithmic method for addressing nonparametric invariance and causality learning in regression models across multiple environments, where the joint distribution of response variables and covariates varies, but the conditional expectations of o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04715v2-abstract-full').style.display = 'inline'; document.getElementById('2405.04715v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.04715v2-abstract-full" style="display: none;"> Pursuing causality from data is a fundamental problem in scientific discovery, treatment intervention, and transfer learning. This paper introduces a novel algorithmic method for addressing nonparametric invariance and causality learning in regression models across multiple environments, where the joint distribution of response variables and covariates varies, but the conditional expectations of outcome given an unknown set of quasi-causal variables are invariant. The challenge of finding such an unknown set of quasi-causal or invariant variables is compounded by the presence of endogenous variables that have heterogeneous effects across different environments, including even one of them in the regression would make the estimation inconsistent. The proposed Focused Adversial Invariant Regularization (FAIR) framework utilizes an innovative minimax optimization approach that breaks down the barriers, driving regression models toward prediction-invariant solutions through adversarial testing. Leveraging the representation power of neural networks, FAIR neural networks (FAIR-NN) are introduced for causality pursuit. It is shown that FAIR-NN can find the invariant variables and quasi-causal variables under a minimal identification condition and that the resulting procedure is adaptive to low-dimensional composition structures in a non-asymptotic analysis. Under a structural causal model, variables identified by FAIR-NN represent pragmatic causality and provably align with exact causal mechanisms under conditions of sufficient heterogeneity. Computationally, FAIR-NN employs a novel Gumbel approximation with decreased temperature and stochastic gradient descent ascent algorithm. The procedures are convincingly demonstrated using simulated and real-data examples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04715v2-abstract-full').style.display = 'none'; document.getElementById('2405.04715v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">48 pages, 7 figures with appendix</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 62G08 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.01851">arXiv:2405.01851</a> <span> [<a href="https://arxiv.org/pdf/2405.01851">pdf</a>, <a href="https://arxiv.org/format/2405.01851">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sicong Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wentao Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zimu Zhou</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Minfan Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zheng Lin</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiwen Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.01851v1-abstract-short" style="display: inline;"> There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the mobile devices hold potential to accelerate DL inference via parallel execution across heterogeneous processors. Various efficient parallel methods have been e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01851v1-abstract-full').style.display = 'inline'; document.getElementById('2405.01851v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.01851v1-abstract-full" style="display: none;"> There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the mobile devices hold potential to accelerate DL inference via parallel execution across heterogeneous processors. Various efficient parallel methods have been explored to optimize computation distribution, achieve load balance, and minimize communication cost across processors. Yet their practical effectiveness in the dynamic and diverse real-world mobile environment is less explored. This paper presents a holistic empirical study to assess the capabilities and challenges associated with parallel DL inference on heterogeneous mobile processors. Through carefully designed experiments covering various DL models, mobile software/hardware environments, workload patterns, and resource availability, we identify limitations of existing techniques and highlight opportunities for cross-level optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01851v1-abstract-full').style.display = 'none'; document.getElementById('2405.01851v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.01466">arXiv:2405.01466</a> <span> [<a href="https://arxiv.org/pdf/2405.01466">pdf</a>, <a href="https://arxiv.org/format/2405.01466">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 Systematic Literature Review on Large Language Models for Automated Program Repair </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Yang Xie</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">YuXiang Ma</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weisong Sun</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yun Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenyu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.01466v2-abstract-short" style="display: inline;"> Automated Program Repair (APR) attempts to patch software bugs and reduce manual debugging efforts. Very recently, with the advances in Large Language Models (LLMs), an increasing number of APR techniques have been proposed, facilitating software development and maintenance and demonstrating remarkable performance. However, due to ongoing explorations in the LLM-based APR field, it is challenging… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01466v2-abstract-full').style.display = 'inline'; document.getElementById('2405.01466v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.01466v2-abstract-full" style="display: none;"> Automated Program Repair (APR) attempts to patch software bugs and reduce manual debugging efforts. Very recently, with the advances in Large Language Models (LLMs), an increasing number of APR techniques have been proposed, facilitating software development and maintenance and demonstrating remarkable performance. However, due to ongoing explorations in the LLM-based APR field, it is challenging for researchers to understand the current achievements, challenges, and potential opportunities. This work provides the first systematic literature review to summarize the applications of LLMs in APR between 2020 and 2024. We analyze 127 relevant papers from LLMs, APR and their integration perspectives. First, we categorize existing popular LLMs that are applied to support APR and outline three types of utilization strategies for their deployment. Besides, we detail some specific repair scenarios that benefit from LLMs, e.g., semantic bugs and security vulnerabilities. Furthermore, we discuss several critical aspects of integrating LLMs into APR research, e.g., input forms and open science. Finally, we highlight a set of challenges remaining to be investigated and the potential guidelines for future research. Overall, our paper provides a systematic overview of the research landscape to the APR community, helping researchers gain a comprehensive understanding of achievements and promote future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01466v2-abstract-full').style.display = 'none'; document.getElementById('2405.01466v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">update new 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/2404.11589">arXiv:2404.11589</a> <span> [<a href="https://arxiv.org/pdf/2404.11589">pdf</a>, <a href="https://arxiv.org/format/2404.11589">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </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/10.1145/3589335.3651927">10.1145/3589335.3651927 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fan%2C+Z">Zezhong Fan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaohan Li</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chenhao Fang</a>, <a href="/search/cs?searchtype=author&query=Biswas%2C+T">Topojoy Biswas</a>, <a href="/search/cs?searchtype=author&query=Nag%2C+K">Kaushiki Nag</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jianpeng Xu</a>, <a href="/search/cs?searchtype=author&query=Achan%2C+K">Kannan Achan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.11589v1-abstract-short" style="display: inline;"> The rapid evolution of text-to-image diffusion models has opened the door of generative AI, enabling the translation of textual descriptions into visually compelling images with remarkable quality. However, a persistent challenge within this domain is the optimization of prompts to effectively convey abstract concepts into concrete objects. For example, text encoders can hardly express "peace", wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11589v1-abstract-full').style.display = 'inline'; document.getElementById('2404.11589v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.11589v1-abstract-full" style="display: none;"> The rapid evolution of text-to-image diffusion models has opened the door of generative AI, enabling the translation of textual descriptions into visually compelling images with remarkable quality. However, a persistent challenge within this domain is the optimization of prompts to effectively convey abstract concepts into concrete objects. For example, text encoders can hardly express "peace", while can easily illustrate olive branches and white doves. This paper introduces a novel approach named Prompt Optimizer for Abstract Concepts (POAC) specifically designed to enhance the performance of text-to-image diffusion models in interpreting and generating images from abstract concepts. We propose a Prompt Language Model (PLM), which is initialized from a pre-trained language model, and then fine-tuned with a curated dataset of abstract concept prompts. The dataset is created with GPT-4 to extend the abstract concept to a scene and concrete objects. Our framework employs a Reinforcement Learning (RL)-based optimization strategy, focusing on the alignment between the generated images by a stable diffusion model and optimized prompts. Through extensive experiments, we demonstrate that our proposed POAC significantly improves the accuracy and aesthetic quality of generated images, particularly in the description of abstract concepts and alignment with optimized prompts. We also present a comprehensive analysis of our model's performance across diffusion models under different settings, showcasing its versatility and effectiveness in enhancing abstract concept representation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11589v1-abstract-full').style.display = 'none'; document.getElementById('2404.11589v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">WWW 2024 Companion</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08695">arXiv:2404.08695</a> <span> [<a href="https://arxiv.org/pdf/2404.08695">pdf</a>, <a href="https://arxiv.org/format/2404.08695">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+F">Feihu Jiang</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+C">Chuan Qin</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+K">Kaichun Yao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Chuyu Fang</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+F">Fuzhen Zhuang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Hengshu Zhu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+H">Hui Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.08695v2-abstract-short" style="display: inline;"> Efficient knowledge management plays a pivotal role in augmenting both the operational efficiency and the innovative capacity of businesses and organizations. By indexing knowledge through vectorization, a variety of knowledge retrieval methods have emerged, significantly enhancing the efficacy of knowledge management systems. Recently, the rapid advancements in generative natural language process… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08695v2-abstract-full').style.display = 'inline'; document.getElementById('2404.08695v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08695v2-abstract-full" style="display: none;"> Efficient knowledge management plays a pivotal role in augmenting both the operational efficiency and the innovative capacity of businesses and organizations. By indexing knowledge through vectorization, a variety of knowledge retrieval methods have emerged, significantly enhancing the efficacy of knowledge management systems. Recently, the rapid advancements in generative natural language processing technologies paved the way for generating precise and coherent answers after retrieving relevant documents tailored to user queries. However, for enterprise knowledge bases, assembling extensive training data from scratch for knowledge retrieval and generation is a formidable challenge due to the privacy and security policies of private data, frequently entailing substantial costs. To address the challenge above, in this paper, we propose EKRG, a novel Retrieval-Generation framework based on large language models (LLMs), expertly designed to enable question-answering for Enterprise Knowledge bases with limited annotation costs. Specifically, for the retrieval process, we first introduce an instruction-tuning method using an LLM to generate sufficient document-question pairs for training a knowledge retriever. This method, through carefully designed instructions, efficiently generates diverse questions for enterprise knowledge bases, encompassing both fact-oriented and solution-oriented knowledge. Additionally, we develop a relevance-aware teacher-student learning strategy to further enhance the efficiency of the training process. For the generation process, we propose a novel chain of thought (CoT) based fine-tuning method to empower the LLM-based generator to adeptly respond to user questions using retrieved documents. Finally, extensive experiments on real-world datasets have demonstrated the effectiveness of our proposed framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08695v2-abstract-full').style.display = 'none'; document.getElementById('2404.08695v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">DASFAA 2024 Accepted</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.17032">arXiv:2403.17032</a> <span> [<a href="https://arxiv.org/pdf/2403.17032">pdf</a>, <a href="https://arxiv.org/ps/2403.17032">ps</a>, <a href="https://arxiv.org/format/2403.17032">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"> Stochastic parameter reduced-order model based on hybrid machine learning approaches </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+J">Jinqiao Duan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.17032v1-abstract-short" style="display: inline;"> Establishing appropriate mathematical models for complex systems in natural phenomena not only helps deepen our understanding of nature but can also be used for state estimation and prediction. However, the extreme complexity of natural phenomena makes it extremely challenging to develop full-order models (FOMs) and apply them to studying many quantities of interest. In contrast, appropriate reduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17032v1-abstract-full').style.display = 'inline'; document.getElementById('2403.17032v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17032v1-abstract-full" style="display: none;"> Establishing appropriate mathematical models for complex systems in natural phenomena not only helps deepen our understanding of nature but can also be used for state estimation and prediction. However, the extreme complexity of natural phenomena makes it extremely challenging to develop full-order models (FOMs) and apply them to studying many quantities of interest. In contrast, appropriate reduced-order models (ROMs) are favored due to their high computational efficiency and ability to describe the key dynamics and statistical characteristics of natural phenomena. Taking the viscous Burgers equation as an example, this paper constructs a Convolutional Autoencoder-Reservoir Computing-Normalizing Flow algorithm framework, where the Convolutional Autoencoder is used to construct latent space representations, and the Reservoir Computing-Normalizing Flow framework is used to characterize the evolution of latent state variables. In this way, a data-driven stochastic parameter reduced-order model is constructed to describe the complex system and its dynamic behavior. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17032v1-abstract-full').style.display = 'none'; document.getElementById('2403.17032v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.12451">arXiv:2403.12451</a> <span> [<a href="https://arxiv.org/pdf/2403.12451">pdf</a>, <a href="https://arxiv.org/format/2403.12451">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"> End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+L">Lirui Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoxi Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hongming Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yaodong Yang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cong Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qing 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="2403.12451v4-abstract-short" style="display: inline;"> Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as ext… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12451v4-abstract-full').style.display = 'inline'; document.getElementById('2403.12451v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.12451v4-abstract-full" style="display: none;"> Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as extensive domain knowledge is required to interpret symbolic policies. In this paper, we present a neuro-symbolic framework for jointly learning structured states and symbolic policies, whose key idea is to distill the vision foundation model into an efficient perception module and refine it during policy learning. Moreover, we design a pipeline to prompt GPT-4 to generate textual explanations for the learned policies and decisions, significantly reducing users' cognitive load to understand the symbolic policies. We verify the efficacy of our approach on nine Atari tasks and present GPT-generated explanations for policies and decisions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12451v4-abstract-full').style.display = 'none'; document.getElementById('2403.12451v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICML 2024. Project page: https://ins-rl.github.io/</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=Fang%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+C&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository