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 61 results for author: <span class="mathjax">Bui, N</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=Bui%2C+N">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="Bui, N"> </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=Bui%2C+N&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="Bui, N"> <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=Bui%2C+N&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Bui%2C+N&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Bui%2C+N&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.17171">arXiv:2412.17171</a> <span> [<a href="https://arxiv.org/pdf/2412.17171">pdf</a>, <a href="https://arxiv.org/format/2412.17171">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Item Tokenization for Generative Recommendation through Self-Improvement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+R">Runjin Chen</a>, <a href="/search/cs?searchtype=author&query=Ju%2C+M">Mingxuan Ju</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Antypas%2C+D">Dimosthenis Antypas</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+S">Stanley Cai</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiaopeng Wu</a>, <a href="/search/cs?searchtype=author&query=Neves%2C+L">Leonardo Neves</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhangyang Wang</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+N">Neil Shah</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Tong Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.17171v1-abstract-short" style="display: inline;"> Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and generating recommendations in a generative manner. A critical challenge in this approach is the effective tokenization of items, ensuring that they are represented in a form compatible with LLMs. Current item tokenization… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17171v1-abstract-full').style.display = 'inline'; document.getElementById('2412.17171v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.17171v1-abstract-full" style="display: none;"> Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and generating recommendations in a generative manner. A critical challenge in this approach is the effective tokenization of items, ensuring that they are represented in a form compatible with LLMs. Current item tokenization methods include using text descriptions, numerical strings, or sequences of discrete tokens. While text-based representations integrate seamlessly with LLM tokenization, they are often too lengthy, leading to inefficiencies and complicating accurate generation. Numerical strings, while concise, lack semantic depth and fail to capture meaningful item relationships. Tokenizing items as sequences of newly defined tokens has gained traction, but it often requires external models or algorithms for token assignment. These external processes may not align with the LLM's internal pretrained tokenization schema, leading to inconsistencies and reduced model performance. To address these limitations, we propose a self-improving item tokenization method that allows the LLM to refine its own item tokenizations during training process. Our approach starts with item tokenizations generated by any external model and periodically adjusts these tokenizations based on the LLM's learned patterns. Such alignment process ensures consistency between the tokenization and the LLM's internal understanding of the items, leading to more accurate recommendations. Furthermore, our method is simple to implement and can be integrated as a plug-and-play enhancement into existing generative recommendation systems. Experimental results on multiple datasets and using various initial tokenization strategies demonstrate the effectiveness of our method, with an average improvement of 8\% in recommendation performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17171v1-abstract-full').style.display = 'none'; document.getElementById('2412.17171v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.15413">arXiv:2411.15413</a> <span> [<a href="https://arxiv.org/pdf/2411.15413">pdf</a>, <a href="https://arxiv.org/format/2411.15413">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"> FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pham%2C+T+T">Trong Thang Pham</a>, <a href="/search/cs?searchtype=author&query=Ho%2C+N">Ngoc-Vuong Ho</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thinh Phan</a>, <a href="/search/cs?searchtype=author&query=Brijesh%2C+P">Patel Brijesh</a>, <a href="/search/cs?searchtype=author&query=Adjeroh%2C+D">Donald Adjeroh</a>, <a href="/search/cs?searchtype=author&query=Doretto%2C+G">Gianfranco Doretto</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A">Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C+C">Carol C. Wu</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hien Nguyen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</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="2411.15413v1-abstract-short" style="display: inline;"> Developing an interpretable system for generating reports in chest X-ray (CXR) analysis is becoming increasingly crucial in Computer-aided Diagnosis (CAD) systems, enabling radiologists to comprehend the decisions made by these systems. Despite the growth of diverse datasets and methods focusing on report generation, there remains a notable gap in how closely these models' generated reports align… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15413v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15413v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15413v1-abstract-full" style="display: none;"> Developing an interpretable system for generating reports in chest X-ray (CXR) analysis is becoming increasingly crucial in Computer-aided Diagnosis (CAD) systems, enabling radiologists to comprehend the decisions made by these systems. Despite the growth of diverse datasets and methods focusing on report generation, there remains a notable gap in how closely these models' generated reports align with the interpretations of real radiologists. In this study, we tackle this challenge by initially introducing Fine-Grained CXR (FG-CXR) dataset, which provides fine-grained paired information between the captions generated by radiologists and the corresponding gaze attention heatmaps for each anatomy. Unlike existing datasets that include a raw sequence of gaze alongside a report, with significant misalignment between gaze location and report content, our FG-CXR dataset offers a more grained alignment between gaze attention and diagnosis transcript. Furthermore, our analysis reveals that simply applying black-box image captioning methods to generate reports cannot adequately explain which information in CXR is utilized and how long needs to attend to accurately generate reports. Consequently, we propose a novel explainable radiologist's attention generator network (Gen-XAI) that mimics the diagnosis process of radiologists, explicitly constraining its output to closely align with both radiologist's gaze attention and transcript. Finally, we perform extensive experiments to illustrate the effectiveness of our method. Our datasets and checkpoint is available at https://github.com/UARK-AICV/FG-CXR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15413v1-abstract-full').style.display = 'none'; document.getElementById('2411.15413v1-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 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">ACCV 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23402">arXiv:2410.23402</a> <span> [<a href="https://arxiv.org/pdf/2410.23402">pdf</a>, <a href="https://arxiv.org/format/2410.23402">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"> VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+C+C">Cuong Chi Le</a>, <a href="/search/cs?searchtype=author&query=Truong-Vinh%2C+H">Hoang-Chau Truong-Vinh</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Huy Nhat Phan</a>, <a href="/search/cs?searchtype=author&query=Le%2C+D+D">Dung Duy Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2410.23402v3-abstract-short" style="display: inline;"> Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce VisualCoder, a simple yet effective approach that enhances code reasoning by integrating… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23402v3-abstract-full').style.display = 'inline'; document.getElementById('2410.23402v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23402v3-abstract-full" style="display: none;"> Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce VisualCoder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with a visual Control Flow Graph (CFG). By aligning code snippets with their corresponding CFGs, VisualCoder provides deeper insights into execution flows. We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23402v3-abstract-full').style.display = 'none'; document.getElementById('2410.23402v3-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 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">NAACL 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.01999">arXiv:2410.01999</a> <span> [<a href="https://arxiv.org/pdf/2410.01999">pdf</a>, <a href="https://arxiv.org/format/2410.01999">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"> CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Manh%2C+D+N">Dung Nguyen Manh</a>, <a href="/search/cs?searchtype=author&query=Chau%2C+T+P">Thang Phan Chau</a>, <a href="/search/cs?searchtype=author&query=Hai%2C+N+L">Nam Le Hai</a>, <a href="/search/cs?searchtype=author&query=Doan%2C+T+T">Thong T. Doan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+V">Nam V. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+Q">Quang Pham</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2410.01999v2-abstract-short" style="display: inline;"> Recent advancements in Code Large Language Models (CodeLLMs) have predominantly focused on open-ended code generation tasks, often neglecting the critical aspect of code understanding and comprehension. To bridge this gap, we present CodeMMLU, a comprehensive multiple-choice question-answer benchmark designed to evaluate the depth of software and code understanding in LLMs. CodeMMLU includes over… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01999v2-abstract-full').style.display = 'inline'; document.getElementById('2410.01999v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01999v2-abstract-full" style="display: none;"> Recent advancements in Code Large Language Models (CodeLLMs) have predominantly focused on open-ended code generation tasks, often neglecting the critical aspect of code understanding and comprehension. To bridge this gap, we present CodeMMLU, a comprehensive multiple-choice question-answer benchmark designed to evaluate the depth of software and code understanding in LLMs. CodeMMLU includes over 10,000 questions sourced from diverse domains, encompassing tasks such as code analysis, defect detection, and software engineering principles across multiple programming languages. Unlike traditional benchmarks, CodeMMLU assesses models's ability to reason about code rather than merely generate it, providing deeper insights into their grasp of complex software concepts and systems. Our extensive evaluation reveals that even state-of-the-art models face significant challenges with CodeMMLU, highlighting deficiencies in comprehension beyond code generation. By underscoring the crucial relationship between code understanding and effective generation, CodeMMLU serves as a vital resource for advancing AI-assisted software development, ultimately aiming to create more reliable and capable coding assistants. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01999v2-abstract-full').style.display = 'none'; document.getElementById('2410.01999v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16299">arXiv:2409.16299</a> <span> [<a href="https://arxiv.org/pdf/2409.16299">pdf</a>, <a href="https://arxiv.org/format/2409.16299">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"> HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Huy Nhat Phan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+P+X">Phong X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2409.16299v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16299v2-abstract-full').style.display = 'inline'; document.getElementById('2409.16299v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16299v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16299v2-abstract-full').style.display = 'none'; document.getElementById('2409.16299v2-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 9 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">49 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/2409.12177">arXiv:2409.12177</a> <span> [<a href="https://arxiv.org/pdf/2409.12177">pdf</a>, <a href="https://arxiv.org/format/2409.12177">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiasheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jialin Chen</a>, <a href="/search/cs?searchtype=author&query=Maatouk%2C+A">Ali Maatouk</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Q">Qianqian Xie</a>, <a href="/search/cs?searchtype=author&query=Tassiulas%2C+L">Leandros Tassiulas</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+J">Jie Shao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hua Xu</a>, <a href="/search/cs?searchtype=author&query=Ying%2C+R">Rex Ying</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="2409.12177v1-abstract-short" style="display: inline;"> With the advent of large language models (LLMs), managing scientific literature via LLMs has become a promising direction of research. However, existing approaches often overlook the rich structural and semantic relevance among scientific literature, limiting their ability to discern the relationships between pieces of scientific knowledge, and suffer from various types of hallucinations. These me… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12177v1-abstract-full').style.display = 'inline'; document.getElementById('2409.12177v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12177v1-abstract-full" style="display: none;"> With the advent of large language models (LLMs), managing scientific literature via LLMs has become a promising direction of research. However, existing approaches often overlook the rich structural and semantic relevance among scientific literature, limiting their ability to discern the relationships between pieces of scientific knowledge, and suffer from various types of hallucinations. These methods also focus narrowly on individual downstream tasks, limiting their applicability across use cases. Here we propose LitFM, the first literature foundation model designed for a wide variety of practical downstream tasks on domain-specific literature, with a focus on citation information. At its core, LitFM contains a novel graph retriever to integrate graph structure by navigating citation graphs and extracting relevant literature, thereby enhancing model reliability. LitFM also leverages a knowledge-infused LLM, fine-tuned through a well-developed instruction paradigm. It enables LitFM to extract domain-specific knowledge from literature and reason relationships among them. By integrating citation graphs during both training and inference, LitFM can generalize to unseen papers and accurately assess their relevance within existing literature. Additionally, we introduce new large-scale literature citation benchmark datasets on three academic fields, featuring sentence-level citation information and local context. Extensive experiments validate the superiority of LitFM, achieving 28.1% improvement on retrieval task in precision, and an average improvement of 7.52% over state-of-the-art across six downstream literature-related tasks <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12177v1-abstract-full').style.display = 'none'; document.getElementById('2409.12177v1-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> <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">18 pages, 12 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.06481">arXiv:2409.06481</a> <span> [<a href="https://arxiv.org/pdf/2409.06481">pdf</a>, <a href="https://arxiv.org/format/2409.06481">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"> NeIn: Telling What You Don't Want </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Dinh-Hieu Hoang</a>, <a href="/search/cs?searchtype=author&query=Trinh%2C+Q">Quoc-Huy Trinh</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Truong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Gauch%2C+S">Susan Gauch</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="2409.06481v1-abstract-short" style="display: inline;"> Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving hu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06481v1-abstract-full').style.display = 'inline'; document.getElementById('2409.06481v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.06481v1-abstract-full" style="display: none;"> Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06481v1-abstract-full').style.display = 'none'; document.getElementById('2409.06481v1-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 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/2408.04663">arXiv:2408.04663</a> <span> [<a href="https://arxiv.org/pdf/2408.04663">pdf</a>, <a href="https://arxiv.org/format/2408.04663">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hai%2C+N+L">Nam Le Hai</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2408.04663v1-abstract-short" style="display: inline;"> Code comments provide important information for understanding the source code. They can help developers understand the overall purpose of a function or class, as well as identify bugs and technical debt. However, an overabundance of comments is meaningless and counterproductive. As a result, it is critical to automatically filter out these comments for specific purposes. In this paper, we present… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04663v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04663v1-abstract-full" style="display: none;"> Code comments provide important information for understanding the source code. They can help developers understand the overall purpose of a function or class, as well as identify bugs and technical debt. However, an overabundance of comments is meaningless and counterproductive. As a result, it is critical to automatically filter out these comments for specific purposes. In this paper, we present Dopamin, a Transformer-based tool for dealing with this issue. Our model excels not only in presenting knowledge sharing of common categories across multiple languages, but also in achieving robust performance in comment classification by improving comment representation. As a result, it outperforms the STACC baseline by 3% on the NLBSE'24 Tool Competition dataset in terms of average F1-score, while maintaining a comparable inference time for practical use. The source code is publicity available at https://github.com/FSoft-AI4Code/Dopamin. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04663v1-abstract-full').style.display = 'none'; document.getElementById('2408.04663v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at The 3rd Intl. Workshop on NL-based Software Engineering, 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/2408.04660">arXiv:2408.04660</a> <span> [<a href="https://arxiv.org/pdf/2408.04660">pdf</a>, <a href="https://arxiv.org/format/2408.04660">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> XMainframe: A Large Language Model for Mainframe Modernization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dau%2C+A+T+V">Anh T. V. Dau</a>, <a href="/search/cs?searchtype=author&query=Dao%2C+H+T">Hieu Trung Dao</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A+T">Anh Tuan Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+H+T">Hieu Trung Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+P+X">Phong X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2408.04660v3-abstract-short" style="display: inline;"> Mainframe operating systems, despite their inception in the 1940s, continue to support critical sectors like finance and government. However, these systems are often viewed as outdated, requiring extensive maintenance and modernization. Addressing this challenge necessitates innovative tools that can understand and interact with legacy codebases. To this end, we introduce XMainframe, a state-of-th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04660v3-abstract-full').style.display = 'inline'; document.getElementById('2408.04660v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04660v3-abstract-full" style="display: none;"> Mainframe operating systems, despite their inception in the 1940s, continue to support critical sectors like finance and government. However, these systems are often viewed as outdated, requiring extensive maintenance and modernization. Addressing this challenge necessitates innovative tools that can understand and interact with legacy codebases. To this end, we introduce XMainframe, a state-of-the-art large language model (LLM) specifically designed with knowledge of mainframe legacy systems and COBOL codebases. Our solution involves the creation of an extensive data collection pipeline to produce high-quality training datasets, enhancing XMainframe's performance in this specialized domain. Additionally, we present MainframeBench, a comprehensive benchmark for assessing mainframe knowledge, including multiple-choice questions, question answering, and COBOL code summarization. Our empirical evaluations demonstrate that XMainframe consistently outperforms existing state-of-the-art LLMs across these tasks. Specifically, XMainframe achieves 30% higher accuracy than DeepSeek-Coder on multiple-choice questions, doubles the BLEU score of Mixtral-Instruct 8x7B on question answering, and scores six times higher than GPT-3.5 on COBOL summarization. Our work highlights the potential of XMainframe to drive significant advancements in managing and modernizing legacy systems, thereby enhancing productivity and saving time for software developers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04660v3-abstract-full').style.display = 'none'; document.getElementById('2408.04660v3-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">v1</span> submitted 5 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/2408.02816">arXiv:2408.02816</a> <span> [<a href="https://arxiv.org/pdf/2408.02816">pdf</a>, <a href="https://arxiv.org/format/2408.02816">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"> CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+C+C">Cuong Chi Le</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Hoang Nhat Phan</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Huy Nhat Phan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2408.02816v3-abstract-short" style="display: inline;"> Predicting program behavior without execution is a critical task in software engineering. Existing models often fall short in capturing the dynamic dependencies among program elements. To address this, we present CodeFlow, a novel machine learning-based approach that predicts code coverage and detects runtime errors by learning both static and dynamic dependencies within the code. By using control… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02816v3-abstract-full').style.display = 'inline'; document.getElementById('2408.02816v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02816v3-abstract-full" style="display: none;"> Predicting program behavior without execution is a critical task in software engineering. Existing models often fall short in capturing the dynamic dependencies among program elements. To address this, we present CodeFlow, a novel machine learning-based approach that predicts code coverage and detects runtime errors by learning both static and dynamic dependencies within the code. By using control flow graphs (CFGs), CodeFlow effectively represents all possible execution paths and the statistic relations between different statements, providing a more comprehensive understanding of program behaviors. CodeFlow constructs CFGs to represent possible execution paths and learns vector representations (embeddings) for CFG nodes, capturing static control-flow dependencies. Additionally, it learns dynamic dependencies by leveraging execution traces, which reflect the impacts among statements during execution. This combination enables CodeFlow to accurately predict code coverage and identify runtime errors. Our empirical evaluation demonstrates that CodeFlow significantly improves code coverage prediction accuracy and effectively localizes runtime errors, outperforming state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02816v3-abstract-full').style.display = 'none'; document.getElementById('2408.02816v3-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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">FORGE 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/2406.14507">arXiv:2406.14507</a> <span> [<a href="https://arxiv.org/pdf/2406.14507">pdf</a>, <a href="https://arxiv.org/format/2406.14507">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"> On Newton's Method to Unlearn Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhung Bui</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+X">Xinyang Lu</a>, <a href="/search/cs?searchtype=author&query=Sim%2C+R+H+L">Rachael Hwee Ling Sim</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+S">See-Kiong Ng</a>, <a href="/search/cs?searchtype=author&query=Low%2C+B+K+H">Bryan Kian Hsiang Low</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="2406.14507v2-abstract-short" style="display: inline;"> With the widespread applications of neural networks (NNs) trained on personal data, machine unlearning has become increasingly important for enabling individuals to exercise their personal data ownership, particularly the "right to be forgotten" from trained NNs. Since retraining is computationally expensive, we seek approximate unlearning algorithms for NNs that return identical models to the ret… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14507v2-abstract-full').style.display = 'inline'; document.getElementById('2406.14507v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.14507v2-abstract-full" style="display: none;"> With the widespread applications of neural networks (NNs) trained on personal data, machine unlearning has become increasingly important for enabling individuals to exercise their personal data ownership, particularly the "right to be forgotten" from trained NNs. Since retraining is computationally expensive, we seek approximate unlearning algorithms for NNs that return identical models to the retrained oracle. While Newton's method has been successfully used to approximately unlearn linear models, we observe that adapting it for NN is challenging due to degenerate Hessians that make computing Newton's update impossible. Additionally, we show that when coupled with popular techniques to resolve the degeneracy, Newton's method often incurs offensively large norm updates and empirically degrades model performance post-unlearning. To address these challenges, we propose CureNewton's method, a principle approach that leverages cubic regularization to handle the Hessian degeneracy effectively. The added regularizer eliminates the need for manual finetuning and affords a natural interpretation within the unlearning context. Experiments across different models and datasets show that our method can achieve competitive unlearning performance to the state-of-the-art algorithm in practical unlearning settings, while being theoretically justified and efficient in running time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14507v2-abstract-full').style.display = 'none'; document.getElementById('2406.14507v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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/2406.11927">arXiv:2406.11927</a> <span> [<a href="https://arxiv.org/pdf/2406.11927">pdf</a>, <a href="https://arxiv.org/format/2406.11927">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"> On the Impacts of Contexts on Repository-Level Code Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hai%2C+N+L">Nam Le Hai</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+M">Dung Manh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2406.11927v4-abstract-short" style="display: inline;"> CodeLLMs have gained widespread adoption for code generation tasks, yet their capacity to handle repository-level code generation with complex contextual dependencies remains underexplored. Our work underscores the critical importance of leveraging repository-level contexts to generate executable and functionally correct code. We present RepoExec, a novel benchmark designed to evaluate repository-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11927v4-abstract-full').style.display = 'inline'; document.getElementById('2406.11927v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11927v4-abstract-full" style="display: none;"> CodeLLMs have gained widespread adoption for code generation tasks, yet their capacity to handle repository-level code generation with complex contextual dependencies remains underexplored. Our work underscores the critical importance of leveraging repository-level contexts to generate executable and functionally correct code. We present RepoExec, a novel benchmark designed to evaluate repository-level code generation, with a focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts. Our study examines a controlled scenario where developers specify essential code dependencies (contexts), challenging models to integrate them effectively. Additionally, we introduce an instruction-tuned dataset that enhances CodeLLMs' ability to leverage dependencies, along with a new metric, Dependency Invocation Rate (DIR), to quantify context utilization. Experimental results reveal that while pretrained LLMs demonstrate superior performance in terms of correctness, instruction-tuned models excel in context utilization and debugging capabilities. RepoExec offers a comprehensive evaluation framework for assessing code functionality and alignment with developer intent, thereby advancing the development of more reliable CodeLLMs for real-world applications. The dataset and source code are available at https://github.com/FSoft-AI4Code/RepoExec. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11927v4-abstract-full').style.display = 'none'; document.getElementById('2406.11927v4-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 February, 2025; <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> <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 NAACL 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/2406.11912">arXiv:2406.11912</a> <span> [<a href="https://arxiv.org/pdf/2406.11912">pdf</a>, <a href="https://arxiv.org/format/2406.11912">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"> AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+H">Minh Huynh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Chau%2C+T+P">Thang Phan Chau</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+P+X">Phong X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2406.11912v2-abstract-short" style="display: inline;"> Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assign… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11912v2-abstract-full').style.display = 'inline'; document.getElementById('2406.11912v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11912v2-abstract-full" style="display: none;"> Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11912v2-abstract-full').style.display = 'none'; document.getElementById('2406.11912v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 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">Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.03431">arXiv:2406.03431</a> <span> [<a href="https://arxiv.org/pdf/2406.03431">pdf</a>, <a href="https://arxiv.org/format/2406.03431">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"> CattleFace-RGBT: RGB-T Cattle Facial Landmark Benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Coffman%2C+E">Ethan Coffman</a>, <a href="/search/cs?searchtype=author&query=Clark%2C+R">Reagan Clark</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+T+T">Trong Thang Pham</a>, <a href="/search/cs?searchtype=author&query=Kegley%2C+B">Beth Kegley</a>, <a href="/search/cs?searchtype=author&query=Powell%2C+J+G">Jeremy G. Powell</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jiangchao Zhao</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</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="2406.03431v1-abstract-short" style="display: inline;"> To address this challenge, we introduce CattleFace-RGBT, a RGB-T Cattle Facial Landmark dataset consisting of 2,300 RGB-T image pairs, a total of 4,600 images. Creating a landmark dataset is time-consuming, but AI-assisted annotation can help. However, applying AI to thermal images is challenging due to suboptimal results from direct thermal training and infeasible RGB-thermal alignment due to dif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03431v1-abstract-full').style.display = 'inline'; document.getElementById('2406.03431v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03431v1-abstract-full" style="display: none;"> To address this challenge, we introduce CattleFace-RGBT, a RGB-T Cattle Facial Landmark dataset consisting of 2,300 RGB-T image pairs, a total of 4,600 images. Creating a landmark dataset is time-consuming, but AI-assisted annotation can help. However, applying AI to thermal images is challenging due to suboptimal results from direct thermal training and infeasible RGB-thermal alignment due to different camera views. Therefore, we opt to transfer models trained on RGB to thermal images and refine them using our AI-assisted annotation tool following a semi-automatic annotation approach. Accurately localizing facial key points on both RGB and thermal images enables us to not only discern the cattle's respiratory signs but also measure temperatures to assess the animal's thermal state. To the best of our knowledge, this is the first dataset for the cattle facial landmark on RGB-T images. We conduct benchmarking of the CattleFace-RGBT dataset across various backbone architectures, with the objective of establishing baselines for future research, analysis, and comparison. The dataset and models are at https://github.com/UARK-AICV/CattleFace-RGBT-benchmark <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03431v1-abstract-full').style.display = 'none'; document.getElementById('2406.03431v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.14352">arXiv:2405.14352</a> <span> [<a href="https://arxiv.org/pdf/2405.14352">pdf</a>, <a href="https://arxiv.org/format/2405.14352">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"> Explaining Graph Neural Networks via Structure-aware Interaction Index </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+T">Hieu Trung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ying%2C+R">Rex Ying</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="2405.14352v1-abstract-short" style="display: inline;"> The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability approaches either focus solely on node-wise importance or neglect the graph structure when perturbing the input instance. This paper introduces the Myers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14352v1-abstract-full').style.display = 'inline'; document.getElementById('2405.14352v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.14352v1-abstract-full" style="display: none;"> The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability approaches either focus solely on node-wise importance or neglect the graph structure when perturbing the input instance. This paper introduces the Myerson-Taylor interaction index that internalizes the graph structure into attributing the node values and the interaction values among nodes. Unlike the Shapley-based methods, the Myerson-Taylor index decomposes coalitions into components satisfying a pre-chosen connectivity criterion. We prove that the Myerson-Taylor index is the unique one that satisfies a system of five natural axioms accounting for graph structure and high-order interaction among nodes. Leveraging these properties, we propose Myerson-Taylor Structure-Aware Graph Explainer (MAGE), a novel explainer that uses the second-order Myerson-Taylor index to identify the most important motifs influencing the model prediction, both positively and negatively. Extensive experiments on various graph datasets and models demonstrate that our method consistently provides superior subgraph explanations compared to state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14352v1-abstract-full').style.display = 'none'; document.getElementById('2405.14352v1-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 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">30 pages, ICML'24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.14592">arXiv:2403.14592</a> <span> [<a href="https://arxiv.org/pdf/2403.14592">pdf</a>, <a href="https://arxiv.org/format/2403.14592">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nghiem%2C+K">Khanh Nghiem</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A+M">Anh Minh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2403.14592v1-abstract-short" style="display: inline;"> As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants. AI coding assistants should set clear expectations for usage, integrate with advanced IDE capabilities and existing extensions, use extendable backend designs, and collect app data responsibly for downstream analyses. We propose open q… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14592v1-abstract-full').style.display = 'inline'; document.getElementById('2403.14592v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14592v1-abstract-full" style="display: none;"> As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants. AI coding assistants should set clear expectations for usage, integrate with advanced IDE capabilities and existing extensions, use extendable backend designs, and collect app data responsibly for downstream analyses. We propose open questions and challenges that academia and industry should address to realize the vision of next-generation AI coding assistants. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14592v1-abstract-full').style.display = 'none'; document.getElementById('2403.14592v1-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 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/2403.06095">arXiv:2403.06095</a> <span> [<a href="https://arxiv.org/pdf/2403.06095">pdf</a>, <a href="https://arxiv.org/format/2403.06095">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"> RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Huy N. Phan</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H+N">Hoang N. Phan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</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="2403.06095v4-abstract-short" style="display: inline;"> Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \tool, a multifaceted framework designed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06095v4-abstract-full').style.display = 'inline'; document.getElementById('2403.06095v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.06095v4-abstract-full" style="display: none;"> Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the {\em Repo-level Semantic Graph} (RSG), a novel semantic graph structure that encapsulates the vast context of code repositories. Furthermore, RepoHyper leverages Expand and Refine retrieval method, including a graph expansion and a link prediction algorithm applied to the RSG, enabling the effective retrieval and prioritization of relevant code snippets. Our evaluations show that \tool markedly outperforms existing techniques in repository-level code completion, showcasing enhanced accuracy across various datasets when compared to several strong baselines. Our implementation of RepoHYPER can be found at https://github.com/FSoft-AI4Code/RepoHyper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06095v4-abstract-full').style.display = 'none'; document.getElementById('2403.06095v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.08246">arXiv:2402.08246</a> <span> [<a href="https://arxiv.org/pdf/2402.08246">pdf</a>, <a href="https://arxiv.org/format/2402.08246">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </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/SII58957.2024.10417512">10.1109/SII58957.2024.10417512 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Ant Colony Optimization for Cooperative Inspection Path Planning Using Multiple Unmanned Aerial Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+D+N">Duy Nam Bui</a>, <a href="/search/cs?searchtype=author&query=Duong%2C+T+N">Thuy Ngan Duong</a>, <a href="/search/cs?searchtype=author&query=Phung%2C+M+D">Manh Duong Phung</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.08246v1-abstract-short" style="display: inline;"> This paper presents a new swarm intelligence-based approach to deal with the cooperative path planning problem of unmanned aerial vehicles (UAVs), which is essential for the automatic inspection of infrastructure. The approach uses a 3D model of the structure to generate viewpoints for the UAVs. The calculation of the viewpoints considers the constraints related to the UAV formation model, camera… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08246v1-abstract-full').style.display = 'inline'; document.getElementById('2402.08246v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.08246v1-abstract-full" style="display: none;"> This paper presents a new swarm intelligence-based approach to deal with the cooperative path planning problem of unmanned aerial vehicles (UAVs), which is essential for the automatic inspection of infrastructure. The approach uses a 3D model of the structure to generate viewpoints for the UAVs. The calculation of the viewpoints considers the constraints related to the UAV formation model, camera parameters, and requirements for data post-processing. The viewpoints are then used as input to formulate the path planning as an extended traveling salesman problem and the definition of a new cost function. Ant colony optimization is finally used to solve the problem to yield optimal inspection paths. Experiments with 3D models of real structures have been conducted to evaluate the performance of the proposed approach. The results show that our system is not only capable of generating feasible inspection paths for UAVs but also reducing the path length by 29.47\% for complex structures when compared with another heuristic approach. The source code of the algorithm can be found at https://github.com/duynamrcv/aco_3d_ipp. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08246v1-abstract-full').style.display = 'none'; document.getElementById('2402.08246v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in: 2024 IEEE/SICE International Symposium on System Integration (SII)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.08245">arXiv:2402.08245</a> <span> [<a href="https://arxiv.org/pdf/2402.08245">pdf</a>, <a href="https://arxiv.org/format/2402.08245">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div 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/SII58957.2024.10417519">10.1109/SII58957.2024.10417519 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Self-Reconfigurable V-shape Formation of Multiple UAVs in Narrow Space Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+D+N">Duy Nam Bui</a>, <a href="/search/cs?searchtype=author&query=Phung%2C+M+D">Manh Duong Phung</a>, <a href="/search/cs?searchtype=author&query=Duy%2C+H+P">Hung Pham Duy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.08245v1-abstract-short" style="display: inline;"> This paper presents the design and implementation of a self-reconfigurable V-shape formation controller for multiple unmanned aerial vehicles (UAVs) navigating through narrow spaces in a dense obstacle environment. The selection of the V-shape formation is motivated by its maneuverability and visibility advantages. The main objective is to develop an effective formation control strategy that allow… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08245v1-abstract-full').style.display = 'inline'; document.getElementById('2402.08245v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.08245v1-abstract-full" style="display: none;"> This paper presents the design and implementation of a self-reconfigurable V-shape formation controller for multiple unmanned aerial vehicles (UAVs) navigating through narrow spaces in a dense obstacle environment. The selection of the V-shape formation is motivated by its maneuverability and visibility advantages. The main objective is to develop an effective formation control strategy that allows UAVs to autonomously adjust their positions to form the desired formation while navigating through obstacles. To achieve this, we propose a distributed behavior-based control algorithm that combines the behaviors designed for individual UAVs so that they together navigate the UAVs to their desired positions. The reconfiguration process is automatic, utilizing individual UAV sensing within the formation, allowing for dynamic adaptations such as opening/closing wings or merging into a straight line. Simulation results show that the self-reconfigurable V-shape formation offers adaptability and effectiveness for UAV formations in complex operational scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08245v1-abstract-full').style.display = 'none'; document.getElementById('2402.08245v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in: 2024 IEEE/SICE International Symposium on System Integration (SII)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.10187">arXiv:2312.10187</a> <span> [<a href="https://arxiv.org/pdf/2312.10187">pdf</a>, <a href="https://arxiv.org/format/2312.10187">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Dinh-Hieu Hoang</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thinh Phan</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+B">Brijesh Patel</a>, <a href="/search/cs?searchtype=author&query=Adjeroh%2C+D">Donald Adjeroh</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.10187v2-abstract-short" style="display: inline;"> The electrocardiogram (ECG) is a valuable signal used to assess various aspects of heart health, such as heart rate and rhythm. It plays a crucial role in identifying cardiac conditions and detecting anomalies in ECG data. However, distinguishing between normal and abnormal ECG signals can be a challenging task. In this paper, we propose an approach that leverages anomaly detection to identify unh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10187v2-abstract-full').style.display = 'inline'; document.getElementById('2312.10187v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.10187v2-abstract-full" style="display: none;"> The electrocardiogram (ECG) is a valuable signal used to assess various aspects of heart health, such as heart rate and rhythm. It plays a crucial role in identifying cardiac conditions and detecting anomalies in ECG data. However, distinguishing between normal and abnormal ECG signals can be a challenging task. In this paper, we propose an approach that leverages anomaly detection to identify unhealthy conditions using solely normal ECG data for training. Furthermore, to enhance the information available and build a robust system, we suggest considering both the time series and time-frequency domain aspects of the ECG signal. As a result, we introduce a specialized network called the Multimodal Time and Spectrogram Restoration Network (TSRNet) designed specifically for detecting anomalies in ECG signals. TSRNet falls into the category of restoration-based anomaly detection and draws inspiration from both the time series and spectrogram domains. By extracting representations from both domains, TSRNet effectively captures the comprehensive characteristics of the ECG signal. This approach enables the network to learn robust representations with superior discrimination abilities, allowing it to distinguish between normal and abnormal ECG patterns more effectively. Furthermore, we introduce a novel inference method, termed Peak-based Error, that specifically focuses on ECG peaks, a critical component in detecting abnormalities. The experimental result on the large-scale dataset PTB-XL has demonstrated the effectiveness of our approach in ECG anomaly detection, while also prioritizing efficiency by minimizing the number of trainable parameters. Our code is available at https://github.com/UARK-AICV/TSRNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10187v2-abstract-full').style.display = 'none'; document.getElementById('2312.10187v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ISBI 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/2312.05634">arXiv:2312.05634</a> <span> [<a href="https://arxiv.org/pdf/2312.05634">pdf</a>, <a href="https://arxiv.org/format/2312.05634">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"> PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trinh%2C+Q">Quoc-Huy Trinh</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Dinh-Hieu Hoang</a>, <a href="/search/cs?searchtype=author&query=Thi%2C+P+V">Phuoc-Thao Vo Thi</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hai-Dang Nguyen</a>, <a href="/search/cs?searchtype=author&query=Jha%2C+D">Debesh Jha</a>, <a href="/search/cs?searchtype=author&query=Bagci%2C+U">Ulas Bagci</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.05634v3-abstract-short" style="display: inline;"> Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05634v3-abstract-full').style.display = 'inline'; document.getElementById('2312.05634v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.05634v3-abstract-full" style="display: none;"> Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module (PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05634v3-abstract-full').style.display = 'none'; document.getElementById('2312.05634v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at AVSS 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/2311.11349">arXiv:2311.11349</a> <span> [<a href="https://arxiv.org/pdf/2311.11349">pdf</a>, <a href="https://arxiv.org/format/2311.11349">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"> Coverage-Validity-Aware Algorithmic Recourse </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+M">Man-Chung Yue</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.11349v2-abstract-short" style="display: inline;"> Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency, and ethics of machine learning models. Existing algorithmic recourse approaches often assume an invariant predictive model; however, the predictive model is usually updated upon the arrival of new data. Thus, a recourse that is valid respective to the present model may become invalid for the future m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11349v2-abstract-full').style.display = 'inline'; document.getElementById('2311.11349v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.11349v2-abstract-full" style="display: none;"> Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency, and ethics of machine learning models. Existing algorithmic recourse approaches often assume an invariant predictive model; however, the predictive model is usually updated upon the arrival of new data. Thus, a recourse that is valid respective to the present model may become invalid for the future model. To resolve this issue, we propose a novel framework to generate a model-agnostic recourse that exhibits robustness to model shifts. Our framework first builds a coverage-validity-aware linear surrogate of the nonlinear (black-box) model; then, the recourse is generated with respect to the linear surrogate. We establish a theoretical connection between our coverage-validity-aware linear surrogate and the minimax probability machines (MPM). We then prove that by prescribing different covariance robustness, the proposed framework recovers popular regularizations for MPM, including the $\ell_2$-regularization and class-reweighting. Furthermore, we show that our surrogate pushes the approximate hyperplane intuitively, facilitating not only robust but also interpretable recourses. The numerical results demonstrate the usefulness and robustness of our framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11349v2-abstract-full').style.display = 'none'; document.getElementById('2311.11349v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.03366">arXiv:2311.03366</a> <span> [<a href="https://arxiv.org/pdf/2311.03366">pdf</a>, <a href="https://arxiv.org/format/2311.03366">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Functional Overlap Reranking for Neural Code Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=To%2C+H+Q">Hung Quoc To</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+H">Minh Huynh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.03366v4-abstract-short" style="display: inline;"> Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often overlooked the intricate functional similarities and interactions between solution clusters. We introduce SRank, a novel reranking strategy for selecting the best solutions from code… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03366v4-abstract-full').style.display = 'inline'; document.getElementById('2311.03366v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.03366v4-abstract-full" style="display: none;"> Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often overlooked the intricate functional similarities and interactions between solution clusters. We introduce SRank, a novel reranking strategy for selecting the best solutions from code generation, focusing on modeling the relationships between clusters of solutions. By quantifying the functional overlap between solution clusters, our approach provides a better ranking strategy for code solutions. Empirical results show that our method achieves remarkable results on the pass@1 score. For instance, on the Human-Eval benchmark, we achieve 69.66% in pass@1 with Codex002, 75.31% with WizardCoder, 53.99% with StarCoder, and 60.55% with CodeGen, surpassing state-of-the-art code generation reranking methods such as CodeT and Coder-Reviewer on the same CodeLLM by a significant margin (approximately 6.1% improvement on average). Even in scenarios with a limited number of sampled solutions and test cases, our approach demonstrates robustness and superiority, marking a new benchmark in code generation reranking. Our implementation can be found at https://github.com/FSoft-AI4Code/SRank-CodeRanker. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03366v4-abstract-full').style.display = 'none'; document.getElementById('2311.03366v4-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ACL 2024, Long Findings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.03493">arXiv:2309.03493</a> <span> [<a href="https://arxiv.org/pdf/2309.03493">pdf</a>, <a href="https://arxiv.org/format/2309.03493">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> SAM3D: Segment Anything Model in Volumetric Medical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Dinh-Hieu Hoang</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Doretto%2C+G">Gianfranco Doretto</a>, <a href="/search/cs?searchtype=author&query=Adjeroh%2C+D">Donald Adjeroh</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+B">Brijesh Patel</a>, <a href="/search/cs?searchtype=author&query=Choudhary%2C+A">Arabinda Choudhary</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.03493v4-abstract-short" style="display: inline;"> Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices. With the advent of deep learning, automated image segmentation methods have risen to prominence, showcasing exceptional proficiency in processing medical imagery. Motivated by the Segment Anything Model (SAM)-a foundational model renowned for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.03493v4-abstract-full').style.display = 'inline'; document.getElementById('2309.03493v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.03493v4-abstract-full" style="display: none;"> Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices. With the advent of deep learning, automated image segmentation methods have risen to prominence, showcasing exceptional proficiency in processing medical imagery. Motivated by the Segment Anything Model (SAM)-a foundational model renowned for its remarkable precision and robust generalization capabilities in segmenting 2D natural images-we introduce SAM3D, an innovative adaptation tailored for 3D volumetric medical image analysis. Unlike current SAM-based methods that segment volumetric data by converting the volume into separate 2D slices for individual analysis, our SAM3D model processes the entire 3D volume image in a unified approach. Extensive experiments are conducted on multiple medical image datasets to demonstrate that our network attains competitive results compared with other state-of-the-art methods in 3D medical segmentation tasks while being significantly efficient in terms of parameters. Code and checkpoints are available at https://github.com/UARK-AICV/SAM3D. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.03493v4-abstract-full').style.display = 'none'; document.getElementById('2309.03493v4-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ISBI 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/2309.03329">arXiv:2309.03329</a> <span> [<a href="https://arxiv.org/pdf/2309.03329">pdf</a>, <a href="https://arxiv.org/format/2309.03329">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"> MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Dinh-Hieu Hoang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+Q">Quang-Thuc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N">Ngan Le</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.03329v3-abstract-short" style="display: inline;"> Efficient polyp segmentation in healthcare plays a critical role in enabling early diagnosis of colorectal cancer. However, the segmentation of polyps presents numerous challenges, including the intricate distribution of backgrounds, variations in polyp sizes and shapes, and indistinct boundaries. Defining the boundary between the foreground (i.e. polyp itself) and the background (surrounding tiss… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.03329v3-abstract-full').style.display = 'inline'; document.getElementById('2309.03329v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.03329v3-abstract-full" style="display: none;"> Efficient polyp segmentation in healthcare plays a critical role in enabling early diagnosis of colorectal cancer. However, the segmentation of polyps presents numerous challenges, including the intricate distribution of backgrounds, variations in polyp sizes and shapes, and indistinct boundaries. Defining the boundary between the foreground (i.e. polyp itself) and the background (surrounding tissue) is difficult. To mitigate these challenges, we propose Multi-Scale Edge-Guided Attention Network (MEGANet) tailored specifically for polyp segmentation within colonoscopy images. This network draws inspiration from the fusion of a classical edge detection technique with an attention mechanism. By combining these techniques, MEGANet effectively preserves high-frequency information, notably edges and boundaries, which tend to erode as neural networks deepen. MEGANet is designed as an end-to-end framework, encompassing three key modules: an encoder, which is responsible for capturing and abstracting the features from the input image, a decoder, which focuses on salient features, and the Edge-Guided Attention module (EGA) that employs the Laplacian Operator to accentuate polyp boundaries. Extensive experiments, both qualitative and quantitative, on five benchmark datasets, demonstrate that our MEGANet outperforms other existing SOTA methods under six evaluation metrics. Our code is available at https://github.com/UARK-AICV/MEGANet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.03329v3-abstract-full').style.display = 'none'; document.getElementById('2309.03329v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 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/2307.02783">arXiv:2307.02783</a> <span> [<a href="https://arxiv.org/pdf/2307.02783">pdf</a>, <a href="https://arxiv.org/format/2307.02783">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thai%2C+T+M">Triet M. Thai</a>, <a href="/search/cs?searchtype=author&query=Vo%2C+A+T">Anh T. Vo</a>, <a href="/search/cs?searchtype=author&query=Tieu%2C+H+K">Hao K. Tieu</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+L+N+P">Linh N. P. Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+T+B">Thien T. B. Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.02783v2-abstract-short" style="display: inline;"> In recent years, artificial intelligence has played an important role in medicine and disease diagnosis, with many applications to be mentioned, one of which is Medical Visual Question Answering (MedVQA). By combining computer vision and natural language processing, MedVQA systems can assist experts in extracting relevant information from medical image based on a given question and providing preci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02783v2-abstract-full').style.display = 'inline'; document.getElementById('2307.02783v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.02783v2-abstract-full" style="display: none;"> In recent years, artificial intelligence has played an important role in medicine and disease diagnosis, with many applications to be mentioned, one of which is Medical Visual Question Answering (MedVQA). By combining computer vision and natural language processing, MedVQA systems can assist experts in extracting relevant information from medical image based on a given question and providing precise diagnostic answers. The ImageCLEFmed-MEDVQA-GI-2023 challenge carried out visual question answering task in the gastrointestinal domain, which includes gastroscopy and colonoscopy images. Our team approached Task 1 of the challenge by proposing a multimodal learning method with image enhancement to improve the VQA performance on gastrointestinal images. The multimodal architecture is set up with BERT encoder and different pre-trained vision models based on convolutional neural network (CNN) and Transformer architecture for features extraction from question and endoscopy image. The result of this study highlights the dominance of Transformer-based vision models over the CNNs and demonstrates the effectiveness of the image enhancement process, with six out of the eight vision models achieving better F1-Score. Our best method, which takes advantages of BERT+BEiT fusion and image enhancement, achieves up to 87.25% accuracy and 91.85% F1-Score on the development test set, while also producing good result on the private test set with accuracy of 82.01%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02783v2-abstract-full').style.display = 'none'; document.getElementById('2307.02783v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ImageCLEF2023 published version: https://ceur-ws.org/Vol-3497/paper-129.pdf</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.08600">arXiv:2306.08600</a> <span> [<a href="https://arxiv.org/pdf/2306.08600">pdf</a>, <a href="https://arxiv.org/format/2306.08600">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> M^2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trinh%2C+Q">Quoc-Huy Trinh</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Mau%2C+T+N">Trong-Hieu Nguyen Mau</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M">Minh-Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H">Hai-Minh Phan</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hai-Dang Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.08600v2-abstract-short" style="display: inline;"> Polyp segmentation has recently garnered significant attention, and multiple methods have been formulated to achieve commendable outcomes. However, these techniques often confront difficulty when working with the complex polyp foreground and their surrounding regions because of the nature of convolution operation. Besides, most existing methods forget to exploit the potential information from mult… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08600v2-abstract-full').style.display = 'inline'; document.getElementById('2306.08600v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.08600v2-abstract-full" style="display: none;"> Polyp segmentation has recently garnered significant attention, and multiple methods have been formulated to achieve commendable outcomes. However, these techniques often confront difficulty when working with the complex polyp foreground and their surrounding regions because of the nature of convolution operation. Besides, most existing methods forget to exploit the potential information from multiple decoder stages. To address this challenge, we suggest combining MetaFormer, introduced as a baseline for integrating CNN and Transformer, with UNet framework and incorporating our Multi-scale Upsampling block (MU). This simple module makes it possible to combine multi-level information by exploring multiple receptive field paths of the shallow decoder stage and then adding with the higher stage to aggregate better feature representation, which is essential in medical image segmentation. Taken all together, we propose MetaFormer Multi-scale Upsampling Network (M$^2$UNet) for the polyp segmentation task. Extensive experiments on five benchmark datasets demonstrate that our method achieved competitive performance compared with several previous methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08600v2-abstract-full').style.display = 'none'; document.getElementById('2306.08600v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.06347">arXiv:2306.06347</a> <span> [<a href="https://arxiv.org/pdf/2306.06347">pdf</a>, <a href="https://arxiv.org/format/2306.06347">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"> DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dau%2C+A+T+V">Anh T. V. Dau</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J+L+C">Jin L. C. Guo</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.06347v3-abstract-short" style="display: inline;"> Comments within source code are essential for developers to comprehend the code's purpose and ensure its correct usage. However, as codebases evolve, maintaining an accurate alignment between the comments and the code becomes increasingly challenging. Recognizing the growing interest in automated solutions for detecting and correcting differences between code and its accompanying comments, current… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.06347v3-abstract-full').style.display = 'inline'; document.getElementById('2306.06347v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.06347v3-abstract-full" style="display: none;"> Comments within source code are essential for developers to comprehend the code's purpose and ensure its correct usage. However, as codebases evolve, maintaining an accurate alignment between the comments and the code becomes increasingly challenging. Recognizing the growing interest in automated solutions for detecting and correcting differences between code and its accompanying comments, current methods rely primarily on heuristic rules. In contrast, this paper presents DocChecker, a tool powered by deep learning. DocChecker is adept at identifying inconsistencies between code and comments, and it can also generate synthetic comments. This capability enables the tool to detect and correct instances where comments do not accurately reflect their corresponding code segments. We demonstrate the effectiveness of DocChecker using the Just-In-Time and CodeXGlue datasets in different settings. Particularly, DocChecker achieves a new State-of-the-art result of 72.3% accuracy on the Inconsistency Code-Comment Detection (ICCD) task and 33.64 BLEU-4 on the code summarization task against other Large Language Models (LLMs), even surpassing GPT 3.5 and CodeLlama. DocChecker is accessible for use and evaluation. It can be found on our GitHub https://github.com/FSoft-AI4Code/DocChecker and as an Online Tool http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on YouTube https://youtu.be/FqnPmd531xw. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.06347v3-abstract-full').style.display = 'none'; document.getElementById('2306.06347v3-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EACL 2024 - Demonstration track </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.00029">arXiv:2306.00029</a> <span> [<a href="https://arxiv.org/pdf/2306.00029">pdf</a>, <a href="https://arxiv.org/format/2306.00029">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"> CodeTF: One-stop Transformer Library for State-of-the-art Code LLM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H">Hung Le</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yue Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Junnan Li</a>, <a href="/search/cs?searchtype=author&query=Gotmare%2C+A+D">Akhilesh Deepak Gotmare</a>, <a href="/search/cs?searchtype=author&query=Hoi%2C+S+C+H">Steven C. H. Hoi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.00029v1-abstract-short" style="display: inline;"> Code intelligence plays a key role in transforming modern software engineering. Recently, deep learning-based models, especially Transformer-based large language models (LLMs), have demonstrated remarkable potential in tackling these tasks by leveraging massive open-source code data and programming language features. However, the development and deployment of such models often require expertise in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00029v1-abstract-full').style.display = 'inline'; document.getElementById('2306.00029v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00029v1-abstract-full" style="display: none;"> Code intelligence plays a key role in transforming modern software engineering. Recently, deep learning-based models, especially Transformer-based large language models (LLMs), have demonstrated remarkable potential in tackling these tasks by leveraging massive open-source code data and programming language features. However, the development and deployment of such models often require expertise in both machine learning and software engineering, creating a barrier for the model adoption. In this paper, we present CodeTF, an open-source Transformer-based library for state-of-the-art Code LLMs and code intelligence. Following the principles of modular design and extensible framework, we design CodeTF with a unified interface to enable rapid access and development across different types of models, datasets and tasks. Our library supports a collection of pretrained Code LLM models and popular code benchmarks, including a standardized interface to train and serve code LLMs efficiently, and data features such as language-specific parsers and utility functions for extracting code attributes. In this paper, we describe the design principles, the architecture, key modules and components, and compare with other related library tools. Finally, we hope CodeTF is able to bridge the gap between machine learning/generative AI and software engineering, providing a comprehensive open-source solution for developers, researchers, and practitioners. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00029v1-abstract-full').style.display = 'none'; document.getElementById('2306.00029v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Ongoing work - Draft Preview</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.07922">arXiv:2305.07922</a> <span> [<a href="https://arxiv.org/pdf/2305.07922">pdf</a>, <a href="https://arxiv.org/format/2305.07922">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> CodeT5+: Open Code Large Language Models for Code Understanding and Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yue Wang</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H">Hung Le</a>, <a href="/search/cs?searchtype=author&query=Gotmare%2C+A+D">Akhilesh Deepak Gotmare</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Junnan Li</a>, <a href="/search/cs?searchtype=author&query=Hoi%2C+S+C+H">Steven C. H. Hoi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.07922v2-abstract-short" style="display: inline;"> Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations in terms of architecture and pretraining tasks. First, they often adopt a specific architecture (encoder-only or decoder-only) or rely on a unified encoder-decoder network for different downstream tasks. The former paradigm is limi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07922v2-abstract-full').style.display = 'inline'; document.getElementById('2305.07922v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.07922v2-abstract-full" style="display: none;"> Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations in terms of architecture and pretraining tasks. First, they often adopt a specific architecture (encoder-only or decoder-only) or rely on a unified encoder-decoder network for different downstream tasks. The former paradigm is limited by inflexibility in applications while in the latter, the model is treated as a single system for all tasks, leading to suboptimal performance on a subset of tasks. Secondly, they often employ a limited set of pretraining objectives which might not be relevant to some downstream tasks and hence result in substantial performance degrade. To address these limitations, we propose ``CodeT5+'', a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. Such flexibility is enabled by our proposed mixture of pretraining objectives to mitigate the pretrain-finetune discrepancy. These objectives cover span denoising, contrastive learning, text-code matching, and causal LM pretraining tasks, on both unimodal and bimodal multilingual code corpora. Furthermore, we propose to initialize CodeT5+ with frozen off-the-shelf LLMs without training from scratch to efficiently scale up our models, and explore instruction-tuning to align with natural language instructions. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning. We observe state-of-the-art (SoTA) model performance on various code-related tasks, such as code generation and completion, math programming, and text-to-code retrieval tasks. Particularly, our instruction-tuned CodeT5+ 16B achieves new SoTA results on HumanEval code generation task against other open code LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07922v2-abstract-full').style.display = 'none'; document.getElementById('2305.07922v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.06156">arXiv:2305.06156</a> <span> [<a href="https://arxiv.org/pdf/2305.06156">pdf</a>, <a href="https://arxiv.org/format/2305.06156">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="Programming Languages">cs.PL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Manh%2C+D+N">Dung Nguyen Manh</a>, <a href="/search/cs?searchtype=author&query=Hai%2C+N+L">Nam Le Hai</a>, <a href="/search/cs?searchtype=author&query=Dau%2C+A+T+V">Anh T. V. Dau</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A+M">Anh Minh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nghiem%2C+K">Khanh Nghiem</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jin Guo</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.06156v2-abstract-short" style="display: inline;"> We present The Vault, a dataset of high-quality code-text pairs in multiple programming languages for training large language models to understand and generate code. We present methods for thoroughly extracting samples that use both rule-based and deep learning-based methods to ensure that they contain high-quality pairs of code and text, resulting in a dataset of 43 million high-quality code-text… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.06156v2-abstract-full').style.display = 'inline'; document.getElementById('2305.06156v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.06156v2-abstract-full" style="display: none;"> We present The Vault, a dataset of high-quality code-text pairs in multiple programming languages for training large language models to understand and generate code. We present methods for thoroughly extracting samples that use both rule-based and deep learning-based methods to ensure that they contain high-quality pairs of code and text, resulting in a dataset of 43 million high-quality code-text pairs. Our extensive evaluations on common coding tasks including code generation, code search and code summarization show that when fine-tuning Code Large Language Models on The Vault, such models outperform the same models trained on other datasets such as CodeSearchNet. We also provide detailed analyses of our datasets to assess the effects of various programming languages and docstrings on the performance of such models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.06156v2-abstract-full').style.display = 'none'; document.getElementById('2305.06156v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at EMNLP 2023, Long Findings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.04605">arXiv:2305.04605</a> <span> [<a href="https://arxiv.org/pdf/2305.04605">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICEET53442.2021.9659578">10.1109/ICEET53442.2021.9659578 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Development of a Vision System to Enhance the Reliability of the Pick-and-Place Robot for Autonomous Testing of Camera Module used in Smartphones </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+H">Hoang-Anh Phan</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+D+N">Duy Nam Bui</a>, <a href="/search/cs?searchtype=author&query=Dinh%2C+T+N">Tuan Nguyen Dinh</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+B">Bao-Anh Hoang</a>, <a href="/search/cs?searchtype=author&query=Ngoc%2C+A+N">An Nguyen Ngoc</a>, <a href="/search/cs?searchtype=author&query=Quoc%2C+D+T+H">Dong Tran Huu Quoc</a>, <a href="/search/cs?searchtype=author&query=Thuy%2C+H+T+T">Ha Tran Thi Thuy</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T+T">Tung Thanh Bui</a>, <a href="/search/cs?searchtype=author&query=Thanh%2C+V+N+T">Van Nguyen Thi Thanh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.04605v1-abstract-short" style="display: inline;"> Pick-and-place robots are commonly used in modern industrial manufacturing. For complex devices/parts like camera modules used in smartphones, which contain optical parts, electrical components and interfacing connectors, the placement operation may not absolutely accurate, which may cause damage in the device under test during the mechanical movement to make good contact for electrical functions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.04605v1-abstract-full').style.display = 'inline'; document.getElementById('2305.04605v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.04605v1-abstract-full" style="display: none;"> Pick-and-place robots are commonly used in modern industrial manufacturing. For complex devices/parts like camera modules used in smartphones, which contain optical parts, electrical components and interfacing connectors, the placement operation may not absolutely accurate, which may cause damage in the device under test during the mechanical movement to make good contact for electrical functions inspection. In this paper, we proposed an effective vision system including hardware and algorithm to enhance the reliability of the pick-and-place robot for autonomous testing memory of camera modules. With limited hardware based on camera and raspberry PI and using simplify image processing algorithm based on histogram information, the vision system can confirm the presence of the camera modules in feeding tray and the placement accuracy of the camera module in test socket. Through that, the system can work with more flexibility and avoid damaging the device under test. The system was experimentally quantified through testing approximately 2000 camera modules in a stable light condition. Experimental results demonstrate that the system achieves accuracy of more than 99.92%. With its simplicity and effectiveness, the proposed vision system can be considered as a useful solution for using in pick-and-place systems in industry. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.04605v1-abstract-full').style.display = 'none'; document.getElementById('2305.04605v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published to 2021 International Conference on Engineering and Emerging Technologies (ICEET 2021). 6 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.01384">arXiv:2305.01384</a> <span> [<a href="https://arxiv.org/pdf/2305.01384">pdf</a>, <a href="https://arxiv.org/format/2305.01384">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Class based Influence Functions for Error Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen-Duc%2C+T">Thang Nguyen-Duc</a>, <a href="/search/cs?searchtype=author&query=Thanh-Tung%2C+H">Hoang Thanh-Tung</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+Q+H">Quan Hung Tran</a>, <a href="/search/cs?searchtype=author&query=Huu-Tien%2C+D">Dang Huu-Tien</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+N">Hieu Ngoc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Dau%2C+A+T+V">Anh T. V. Dau</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.01384v1-abstract-short" style="display: inline;"> Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01384v1-abstract-full').style.display = 'inline'; document.getElementById('2305.01384v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.01384v1-abstract-full" style="display: none;"> Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information to improve the stability of IFs. Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01384v1-abstract-full').style.display = 'none'; document.getElementById('2305.01384v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Thang Nguyen-Duc, Hoang Thanh-Tung, and Quan Hung Tran are co-first authors of this paper. 12 pages, 12 figures. Accepted to ACL 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.01228">arXiv:2304.01228</a> <span> [<a href="https://arxiv.org/pdf/2304.01228">pdf</a>, <a href="https://arxiv.org/format/2304.01228">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Better Language Models of Code through Self-Improvement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=To%2C+H+Q">Hung Quoc To</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jin Guo</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.01228v2-abstract-short" style="display: inline;"> Pre-trained language models for code (PLMCs) have gained attention in recent research. These models are pre-trained on large-scale datasets using multi-modal objectives. However, fine-tuning them requires extensive supervision and is limited by the size of the dataset provided. We aim to improve this issue by proposing a simple data augmentation framework. Our framework utilizes knowledge gained d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.01228v2-abstract-full').style.display = 'inline'; document.getElementById('2304.01228v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.01228v2-abstract-full" style="display: none;"> Pre-trained language models for code (PLMCs) have gained attention in recent research. These models are pre-trained on large-scale datasets using multi-modal objectives. However, fine-tuning them requires extensive supervision and is limited by the size of the dataset provided. We aim to improve this issue by proposing a simple data augmentation framework. Our framework utilizes knowledge gained during the pre-training and fine-tuning stage to generate pseudo data, which is then used as training data for the next step. We incorporate this framework into the state-of-the-art language models, such as CodeT5, CodeBERT, and UnixCoder. The results show that our framework significantly improves PLMCs' performance in code-related sequence generation tasks, such as code summarization and code generation in the CodeXGLUE benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.01228v2-abstract-full').style.display = 'none'; document.getElementById('2304.01228v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to Findings, ACL 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.11213">arXiv:2302.11213</a> <span> [<a href="https://arxiv.org/pdf/2302.11213">pdf</a>, <a href="https://arxiv.org/format/2302.11213">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"> Feasible Recourse Plan via Diverse Interpolation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.11213v1-abstract-short" style="display: inline;"> Explaining algorithmic decisions and recommending actionable feedback is increasingly important for machine learning applications. Recently, significant efforts have been invested in finding a diverse set of recourses to cover the wide spectrum of users' preferences. However, existing works often neglect the requirement that the recourses should be close to the data manifold; hence, the constructe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.11213v1-abstract-full').style.display = 'inline'; document.getElementById('2302.11213v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.11213v1-abstract-full" style="display: none;"> Explaining algorithmic decisions and recommending actionable feedback is increasingly important for machine learning applications. Recently, significant efforts have been invested in finding a diverse set of recourses to cover the wide spectrum of users' preferences. However, existing works often neglect the requirement that the recourses should be close to the data manifold; hence, the constructed recourses might be implausible and unsatisfying to users. To address these issues, we propose a novel approach that explicitly directs the diverse set of actionable recourses towards the data manifold. We first find a diverse set of prototypes in the favorable class that balances the trade-off between diversity and proximity. We demonstrate two specific methods to find these prototypes: either by finding the maximum a posteriori estimate of a determinantal point process or by solving a quadratic binary program. To ensure the actionability constraints, we construct an actionability graph in which the nodes represent the training samples and the edges indicate the feasible action between two instances. We then find a feasible path to each prototype, and this path demonstrates the feasible actions for each recourse in the plan. The experimental results show that our method produces a set of recourses that are close to the data manifold while delivering a better cost-diversity trade-off than existing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.11213v1-abstract-full').style.display = 'none'; document.getElementById('2302.11213v1-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 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/2302.11211">arXiv:2302.11211</a> <span> [<a href="https://arxiv.org/pdf/2302.11211">pdf</a>, <a href="https://arxiv.org/format/2302.11211">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"> Distributionally Robust Recourse Action </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.11211v1-abstract-short" style="display: inline;"> A recourse action aims to explain a particular algorithmic decision by showing one specific way in which the instance could be modified to receive an alternate outcome. Existing recourse generation methods often assume that the machine learning model does not change over time. However, this assumption does not always hold in practice because of data distribution shifts, and in this case, the recou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.11211v1-abstract-full').style.display = 'inline'; document.getElementById('2302.11211v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.11211v1-abstract-full" style="display: none;"> A recourse action aims to explain a particular algorithmic decision by showing one specific way in which the instance could be modified to receive an alternate outcome. Existing recourse generation methods often assume that the machine learning model does not change over time. However, this assumption does not always hold in practice because of data distribution shifts, and in this case, the recourse action may become invalid. To redress this shortcoming, we propose the Distributionally Robust Recourse Action (DiRRAc) framework, which generates a recourse action that has a high probability of being valid under a mixture of model shifts. We formulate the robustified recourse setup as a min-max optimization problem, where the max problem is specified by Gelbrich distance over an ambiguity set around the distribution of model parameters. Then we suggest a projected gradient descent algorithm to find a robust recourse according to the min-max objective. We show that our DiRRAc framework can be extended to hedge against the misspecification of the mixture weights. Numerical experiments with both synthetic and three real-world datasets demonstrate the benefits of our proposed framework over state-of-the-art recourse methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.11211v1-abstract-full').style.display = 'none'; document.getElementById('2302.11211v1-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">25 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/2301.06673">arXiv:2301.06673</a> <span> [<a href="https://arxiv.org/pdf/2301.06673">pdf</a>, <a href="https://arxiv.org/format/2301.06673">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mau%2C+T+N">Trong-Hieu Nguyen Mau</a>, <a href="/search/cs?searchtype=author&query=Trinh%2C+Q">Quoc-Huy Trinh</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhat-Tan Bui</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+M">Minh-Triet Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hai-Dang Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.06673v2-abstract-short" style="display: inline;"> Medical image segmentation is the technique that helps doctor view and has a precise diagnosis, particularly in Colorectal Cancer. Specifically, with the increase in cases, the diagnosis and identification need to be faster and more accurate for many patients; in endoscopic images, the segmentation task has been vital to helping the doctor identify the position of the polyps or the ache in the sys… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06673v2-abstract-full').style.display = 'inline'; document.getElementById('2301.06673v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.06673v2-abstract-full" style="display: none;"> Medical image segmentation is the technique that helps doctor view and has a precise diagnosis, particularly in Colorectal Cancer. Specifically, with the increase in cases, the diagnosis and identification need to be faster and more accurate for many patients; in endoscopic images, the segmentation task has been vital to helping the doctor identify the position of the polyps or the ache in the system correctly. As a result, many efforts have been made to apply deep learning to automate polyp segmentation, mostly to ameliorate the U-shape structure. However, the simple skip connection scheme in UNet leads to deficient context information and the semantic gap between feature maps from the encoder and decoder. To deal with this problem, we propose a novel framework composed of ConvNeXt backbone and Multi Kernel Positional Embedding block. Thanks to the suggested module, our method can attain better accuracy and generalization in the polyps segmentation task. Extensive experiments show that our model achieves the Dice coefficient of 0.8818 and the IOU score of 0.8163 on the Kvasir-SEG dataset. Furthermore, on various datasets, we make competitive achievement results with other previous state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06673v2-abstract-full').style.display = 'none'; document.getElementById('2301.06673v2-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.13209">arXiv:2212.13209</a> <span> [<a href="https://arxiv.org/pdf/2212.13209">pdf</a>, <a href="https://arxiv.org/format/2212.13209">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Deployment of UAVs for Optimal Multihop Ad-hoc Networks Using Particle Swarm Optimization and Behavior-based Control </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thuy%2C+N+D+T">Ngan Duong Thi Thuy</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+D+N">Duy Nam Bui</a>, <a href="/search/cs?searchtype=author&query=Phung%2C+M+D">Manh Duong Phung</a>, <a href="/search/cs?searchtype=author&query=Duy%2C+H+P">Hung Pham Duy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.13209v1-abstract-short" style="display: inline;"> This study proposes an approach for establishing an optimal multihop ad-hoc network using multiple unmanned aerial vehicles (UAVs) to provide emergency communication in disaster areas. The approach includes two stages, one uses particle swarm optimization (PSO) to find optimal positions to deploy UAVs, and the other uses a behavior-based controller to navigate the UAVs to their assigned positions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.13209v1-abstract-full').style.display = 'inline'; document.getElementById('2212.13209v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.13209v1-abstract-full" style="display: none;"> This study proposes an approach for establishing an optimal multihop ad-hoc network using multiple unmanned aerial vehicles (UAVs) to provide emergency communication in disaster areas. The approach includes two stages, one uses particle swarm optimization (PSO) to find optimal positions to deploy UAVs, and the other uses a behavior-based controller to navigate the UAVs to their assigned positions without colliding with obstacles in an unknown environment. Several constraints related to the UAVs' sensing and communication ranges have been imposed to ensure the applicability of the proposed approach in real-world scenarios. A number of simulation experiments with data loaded from real environments have been conducted. The results show that our proposed approach is not only successful in establishing multihop ad-hoc routes but also meets the requirements for real-time deployment of UAVs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.13209v1-abstract-full').style.display = 'none'; document.getElementById('2212.13209v1-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In the 11th International Conference on Control, Automation and Information Sciences (ICCAIS 2022), Hanoi, Vietnam</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.12192">arXiv:2212.12192</a> <span> [<a href="https://arxiv.org/pdf/2212.12192">pdf</a>, <a href="https://arxiv.org/format/2212.12192">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> CinPatent: Datasets for Patent Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+M">Minh-Tien Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Nhung Bui</a>, <a href="/search/cs?searchtype=author&query=Tran-Tien%2C+M">Manh Tran-Tien</a>, <a href="/search/cs?searchtype=author&query=Le%2C+L">Linh Le</a>, <a href="/search/cs?searchtype=author&query=Vu%2C+H">Huy-The Vu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.12192v3-abstract-short" style="display: inline;"> Patent classification is the task that assigns each input patent into several codes (classes). Due to its high demand, several datasets and methods have been introduced. However, the lack of both systematic performance comparison of baselines and access to some datasets creates a gap for the task. To fill the gap, we introduce two new datasets in English and Japanese collected by using CPC codes.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.12192v3-abstract-full').style.display = 'inline'; document.getElementById('2212.12192v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.12192v3-abstract-full" style="display: none;"> Patent classification is the task that assigns each input patent into several codes (classes). Due to its high demand, several datasets and methods have been introduced. However, the lack of both systematic performance comparison of baselines and access to some datasets creates a gap for the task. To fill the gap, we introduce two new datasets in English and Japanese collected by using CPC codes. The English dataset includes 45,131 patent documents with 425 labels and the Japanese dataset contains 54,657 documents with 523 labels. To facilitate the next studies, we compare the performance of strong multi-label text classification methods on the two datasets. Experimental results show that AttentionXML is consistently better than other strong baselines. The ablation study is also conducted in two aspects: the contribution of different parts (title, abstract, description, and claims) of a patent and the behavior of baselines in terms of performance with different training data segmentation. We release the two new datasets with the code of the baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.12192v3-abstract-full').style.display = 'none'; document.getElementById('2212.12192v3-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper describes an on-going work</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.14875">arXiv:2211.14875</a> <span> [<a href="https://arxiv.org/pdf/2211.14875">pdf</a>, <a href="https://arxiv.org/format/2211.14875">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yue Wang</a>, <a href="/search/cs?searchtype=author&query=Hoi%2C+S">Steven Hoi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.14875v3-abstract-short" style="display: inline;"> Automated software debugging is a crucial task for improving the productivity of software developers. Many neural-based techniques have been proven effective for debugging-related tasks such as bug localization and program repair (or bug fixing). However, these techniques often focus only on either one of them or approach them in a stage-wise manner, ignoring the mutual benefits between them. In t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.14875v3-abstract-full').style.display = 'inline'; document.getElementById('2211.14875v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.14875v3-abstract-full" style="display: none;"> Automated software debugging is a crucial task for improving the productivity of software developers. Many neural-based techniques have been proven effective for debugging-related tasks such as bug localization and program repair (or bug fixing). However, these techniques often focus only on either one of them or approach them in a stage-wise manner, ignoring the mutual benefits between them. In this work, we propose a novel unified \emph{Detect-Localize-Repair} framework based on a pretrained programming language model CodeT5 to seamlessly address these tasks, named CodeT5-DLR. Specifically, we propose three objectives to adapt the generic CodeT5 for debugging: a bug detection objective to determine whether a given code snippet is buggy or not, a bug localization objective to identify the buggy lines, and a program repair objective to translate the buggy code to its fixed version. We evaluate it on each of these tasks and their combined setting on two newly collected line-level debugging datasets in Java and Python. Extensive results show that our model significantly outperforms existing baselines from both NLP and software engineering domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.14875v3-abstract-full').style.display = 'none'; document.getElementById('2211.14875v3-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to EMNLP 2022 Findings Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.07824">arXiv:2208.07824</a> <span> [<a href="https://arxiv.org/pdf/2208.07824">pdf</a>, <a href="https://arxiv.org/format/2208.07824">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </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/MASS56207.2022.00097">10.1109/MASS56207.2022.00097 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Deep Reinforcement Learning-based Adaptive Charging Policy for WRSNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+P+L">Phi Le Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Do%2C+P+T">Phan Thuan Do</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.07824v1-abstract-short" style="display: inline;"> Wireless sensor networks consist of randomly distributed sensor nodes for monitoring targets or areas of interest. Maintaining the network for continuous surveillance is a challenge due to the limited battery capacity in each sensor. Wireless power transfer technology is emerging as a reliable solution for energizing the sensors by deploying a mobile charger (MC) to recharge the sensor. However, d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.07824v1-abstract-full').style.display = 'inline'; document.getElementById('2208.07824v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.07824v1-abstract-full" style="display: none;"> Wireless sensor networks consist of randomly distributed sensor nodes for monitoring targets or areas of interest. Maintaining the network for continuous surveillance is a challenge due to the limited battery capacity in each sensor. Wireless power transfer technology is emerging as a reliable solution for energizing the sensors by deploying a mobile charger (MC) to recharge the sensor. However, designing an optimal charging path for the MC is challenging because of uncertainties arising in the networks. The energy consumption rate of the sensors may fluctuate significantly due to unpredictable changes in the network topology, such as node failures. These changes also lead to shifts in the importance of each sensor, which are often assumed to be the same in existing works. We address these challenges in this paper by proposing a novel adaptive charging scheme using a deep reinforcement learning (DRL) approach. Specifically, we endow the MC with a charging policy that determines the next sensor to charge conditioning on the current state of the network. We then use a deep neural network to parametrize this charging policy, which will be trained by reinforcement learning techniques. Our model can adapt to spontaneous changes in the network topology. The empirical results show that the proposed algorithm outperforms the existing on-demand algorithms by a significant margin. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.07824v1-abstract-full').style.display = 'none'; document.getElementById('2208.07824v1-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.10833">arXiv:2206.10833</a> <span> [<a href="https://arxiv.org/pdf/2206.10833">pdf</a>, <a href="https://arxiv.org/format/2206.10833">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"> Robust Bayesian Recourse </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Tuan-Duy H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+M">Man-Chung Yue</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.10833v1-abstract-short" style="display: inline;"> Algorithmic recourse aims to recommend an informative feedback to overturn an unfavorable machine learning decision. We introduce in this paper the Bayesian recourse, a model-agnostic recourse that minimizes the posterior probability odds ratio. Further, we present its min-max robust counterpart with the goal of hedging against future changes in the machine learning model parameters. The robust co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.10833v1-abstract-full').style.display = 'inline'; document.getElementById('2206.10833v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.10833v1-abstract-full" style="display: none;"> Algorithmic recourse aims to recommend an informative feedback to overturn an unfavorable machine learning decision. We introduce in this paper the Bayesian recourse, a model-agnostic recourse that minimizes the posterior probability odds ratio. Further, we present its min-max robust counterpart with the goal of hedging against future changes in the machine learning model parameters. The robust counterpart explicitly takes into account possible perturbations of the data in a Gaussian mixture ambiguity set prescribed using the optimal transport (Wasserstein) distance. We show that the resulting worst-case objective function can be decomposed into solving a series of two-dimensional optimization subproblems, and the min-max recourse finding problem is thus amenable to a gradient descent algorithm. Contrary to existing methods for generating robust recourses, the robust Bayesian recourse does not require a linear approximation step. The numerical experiment demonstrates the effectiveness of our proposed robust Bayesian recourse facing model shifts. Our code is available at https://github.com/VinAIResearch/robust-bayesian-recourse. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.10833v1-abstract-full').style.display = 'none'; document.getElementById('2206.10833v1-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to UAI'22</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.15479">arXiv:2205.15479</a> <span> [<a href="https://arxiv.org/pdf/2205.15479">pdf</a>, <a href="https://arxiv.org/format/2205.15479">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+H">Minh Huynh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Hy%2C+T+S">Truong Son Hy</a>, <a href="/search/cs?searchtype=author&query=Tran-Thanh%2C+L">Long Tran-Thanh</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+N">Tien N. Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.15479v3-abstract-short" style="display: inline;"> We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet. HCRs effectively capture essential code features at lexical, syntactic, and semantic levels by abstracting coarse-grained code elements and incorporating fine-grained program elements in a hierarchical structure. Our HierarchyNet method processes each layer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.15479v3-abstract-full').style.display = 'inline'; document.getElementById('2205.15479v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.15479v3-abstract-full" style="display: none;"> We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet. HCRs effectively capture essential code features at lexical, syntactic, and semantic levels by abstracting coarse-grained code elements and incorporating fine-grained program elements in a hierarchical structure. Our HierarchyNet method processes each layer of the HCR separately through a unique combination of the Heterogeneous Graph Transformer, a Tree-based CNN, and a Transformer Encoder. This approach preserves dependencies between code elements and captures relations through a novel Hierarchical-Aware Cross Attention layer. Our method surpasses current state-of-the-art techniques, such as PA-Former, CAST, and NeuralCodeSum. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.15479v3-abstract-full').style.display = 'none'; document.getElementById('2205.15479v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.13022">arXiv:2205.13022</a> <span> [<a href="https://arxiv.org/pdf/2205.13022">pdf</a>, <a href="https://arxiv.org/ps/2205.13022">ps</a>, <a href="https://arxiv.org/format/2205.13022">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</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/10.1145/3551349.3561168">10.1145/3551349.3561168 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dau%2C+A+T+V">Anh T. V. Dau</a>, <a href="/search/cs?searchtype=author&query=Nguyen-Duc%2C+T">Thang Nguyen-Duc</a>, <a href="/search/cs?searchtype=author&query=Thanh-Tung%2C+H">Hoang Thanh-Tung</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.13022v2-abstract-short" style="display: inline;"> Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use. This is because there could be noise in the source code corpora used to train such models. We adapt data-influence methods to detect such noises in this paper. Data-influence methods are used in machine learning to evaluate the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13022v2-abstract-full').style.display = 'inline'; document.getElementById('2205.13022v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.13022v2-abstract-full" style="display: none;"> Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use. This is because there could be noise in the source code corpora used to train such models. We adapt data-influence methods to detect such noises in this paper. Data-influence methods are used in machine learning to evaluate the similarity of a target sample to the correct samples in order to determine whether or not the target sample is noisy. Our evaluation results show that data-influence methods can identify noisy samples from neural code models in classification-based tasks. This approach will contribute to the larger vision of developing better neural source code models from a data-centric perspective, which is a key driver for developing useful source code models in practice. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13022v2-abstract-full').style.display = 'none'; document.getElementById('2205.13022v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The 37th IEEE/ACM International Conference on Automated Software Engineering</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.12487">arXiv:2201.12487</a> <span> [<a href="https://arxiv.org/pdf/2201.12487">pdf</a>, <a href="https://arxiv.org/format/2201.12487">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"> Counterfactual Plans under Distributional Ambiguity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N">Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+A">Viet Anh Nguyen</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="2201.12487v2-abstract-short" style="display: inline;"> Counterfactual explanations are attracting significant attention due to the flourishing applications of machine learning models in consequential domains. A counterfactual plan consists of multiple possibilities to modify a given instance so that the model's prediction will be altered. As the predictive model can be updated subject to the future arrival of new data, a counterfactual plan may become… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12487v2-abstract-full').style.display = 'inline'; document.getElementById('2201.12487v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.12487v2-abstract-full" style="display: none;"> Counterfactual explanations are attracting significant attention due to the flourishing applications of machine learning models in consequential domains. A counterfactual plan consists of multiple possibilities to modify a given instance so that the model's prediction will be altered. As the predictive model can be updated subject to the future arrival of new data, a counterfactual plan may become ineffective or infeasible with respect to the future values of the model parameters. In this work, we study the counterfactual plans under model uncertainty, in which the distribution of the model parameters is partially prescribed using only the first- and second-moment information. First, we propose an uncertainty quantification tool to compute the lower and upper bounds of the probability of validity for any given counterfactual plan. We then provide corrective methods to adjust the counterfactual plan to improve the validity measure. The numerical experiments validate our bounds and demonstrate that our correction increases the robustness of the counterfactual plans in different real-world datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12487v2-abstract-full').style.display = 'none'; document.getElementById('2201.12487v2-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 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 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/2112.11226">arXiv:2112.11226</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="Programming Languages">cs.PL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Energy-bounded Learning for Robust Models of Code </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yijun 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="2112.11226v2-abstract-short" style="display: inline;"> In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. Various representations of code in terms of tokens, syntax trees, dependency graphs, code navigation paths, or a combination of their variants have been proposed, however, existing vanilla learning techniques have a major limitation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11226v2-abstract-full').style.display = 'inline'; document.getElementById('2112.11226v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.11226v2-abstract-full" style="display: none;"> In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. Various representations of code in terms of tokens, syntax trees, dependency graphs, code navigation paths, or a combination of their variants have been proposed, however, existing vanilla learning techniques have a major limitation in robustness, i.e., it is easy for the models to make incorrect predictions when the inputs are altered in a subtle way. To enhance the robustness, existing approaches focus on recognizing adversarial samples rather than on the valid samples that fall outside a given distribution, which we refer to as out-of-distribution (OOD) samples. Recognizing such OOD samples is the novel problem investigated in this paper. To this end, we propose to first augment the in=distribution datasets with out-of-distribution samples such that, when trained together, they will enhance the model's robustness. We propose the use of an energy-bounded learning objective function to assign a higher score to in-distribution samples and a lower score to out-of-distribution samples in order to incorporate such out-of-distribution samples into the training process of source code models. In terms of OOD detection and adversarial samples detection, our evaluation results demonstrate a greater robustness for existing source code models to become more accurate at recognizing OOD data while being more resistant to adversarial attacks at the same time. Furthermore, the proposed energy-bounded score outperforms all existing OOD detection scores by a large margin, including the softmax confidence score, the Mahalanobis score, and ODIN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11226v2-abstract-full').style.display = 'none'; document.getElementById('2112.11226v2-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </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">There are some flaws in our experiments, we would like to fix it and publish a fixed version again in the very near future</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.00640">arXiv:2111.00640</a> <span> [<a href="https://arxiv.org/pdf/2111.00640">pdf</a>, <a href="https://arxiv.org/format/2111.00640">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> VSEC: Transformer-based Model for Vietnamese Spelling Correction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Do%2C+D">Dinh-Truong Do</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+T">Ha Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T+N">Thang Ngoc Bui</a>, <a href="/search/cs?searchtype=author&query=Vo%2C+D+H">Dinh Hieu Vo</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="2111.00640v2-abstract-short" style="display: inline;"> Spelling error correction is one of topics which have a long history in natural language processing. Although previous studies have achieved remarkable results, challenges still exist. In the Vietnamese language, a state-of-the-art method for the task infers a syllable's context from its adjacent syllables. The method's accuracy can be unsatisfactory, however, because the model may lose the contex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.00640v2-abstract-full').style.display = 'inline'; document.getElementById('2111.00640v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.00640v2-abstract-full" style="display: none;"> Spelling error correction is one of topics which have a long history in natural language processing. Although previous studies have achieved remarkable results, challenges still exist. In the Vietnamese language, a state-of-the-art method for the task infers a syllable's context from its adjacent syllables. The method's accuracy can be unsatisfactory, however, because the model may lose the context if two (or more) spelling mistakes stand near each other. In this paper, we propose a novel method to correct Vietnamese spelling errors. We tackle the problems of mistyped errors and misspelled errors by using a deep learning model. The embedding layer, in particular, is powered by the byte pair encoding technique. The sequence to sequence model based on the Transformer architecture makes our approach different from the previous works on the same problem. In the experiment, we train the model with a large synthetic dataset, which is randomly introduced spelling errors. We test the performance of the proposed method using a realistic dataset. This dataset contains 11,202 human-made misspellings in 9,341 different Vietnamese sentences. The experimental results show that our method achieves encouraging performance with 86.8% errors detected and 81.5% errors corrected, which improves the state-of-the-art approach 5.6% and 2.2%, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.00640v2-abstract-full').style.display = 'none'; document.getElementById('2111.00640v2-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 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.01542">arXiv:2105.01542</a> <span> [<a href="https://arxiv.org/pdf/2105.01542">pdf</a>, <a href="https://arxiv.org/format/2105.01542">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-030-88113-9_44">10.1007/978-3-030-88113-9_44 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Conversational Machine Reading Comprehension for Vietnamese Healthcare Texts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luu%2C+S+T">Son T. Luu</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+M+N">Mao Nguyen Bui</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+D">Loi Duc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+K+V">Khiem Vinh Tran</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</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="2105.01542v6-abstract-short" style="display: inline;"> Machine reading comprehension (MRC) is a sub-field in natural language processing that aims to assist computers understand unstructured texts and then answer questions related to them. In practice, the conversation is an essential way to communicate and transfer information. To help machines understand conversation texts, we present UIT-ViCoQA, a new corpus for conversational machine reading compr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.01542v6-abstract-full').style.display = 'inline'; document.getElementById('2105.01542v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.01542v6-abstract-full" style="display: none;"> Machine reading comprehension (MRC) is a sub-field in natural language processing that aims to assist computers understand unstructured texts and then answer questions related to them. In practice, the conversation is an essential way to communicate and transfer information. To help machines understand conversation texts, we present UIT-ViCoQA, a new corpus for conversational machine reading comprehension in the Vietnamese language. This corpus consists of 10,000 questions with answers over 2,000 conversations about health news articles. Then, we evaluate several baseline approaches for conversational machine comprehension on the UIT-ViCoQA corpus. The best model obtains an F1 score of 45.27%, which is 30.91 points behind human performance (76.18%), indicating that there is ample room for improvement. Our dataset is available at our website: http://nlp.uit.edu.vn/datasets/ for research purposes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.01542v6-abstract-full').style.display = 'none'; document.getElementById('2105.01542v6-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published at The 13th International Conference on Computational Collective Intelligence (ICCCI 2021)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.07023">arXiv:2012.07023</a> <span> [<a href="https://arxiv.org/pdf/2012.07023">pdf</a>, <a href="https://arxiv.org/format/2012.07023">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yijun Yu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+L">Lingxiao Jiang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2012.07023v2-abstract-short" style="display: inline;"> Building deep learning models on source code has found many successful software engineering applications, such as code search, code comment generation, bug detection, code migration, and so on. Current learning techniques, however, have a major drawback that these models are mostly trained on datasets labeled for particular downstream tasks, and code representations may not be suitable for other t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.07023v2-abstract-full').style.display = 'inline'; document.getElementById('2012.07023v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.07023v2-abstract-full" style="display: none;"> Building deep learning models on source code has found many successful software engineering applications, such as code search, code comment generation, bug detection, code migration, and so on. Current learning techniques, however, have a major drawback that these models are mostly trained on datasets labeled for particular downstream tasks, and code representations may not be suitable for other tasks. While some techniques produce representations from unlabeled code, they are far from satisfactory when applied to downstream tasks. Although certain techniques generate representations from unlabeled code when applied to downstream tasks they are far from satisfactory. This paper proposes InferCode to overcome the limitation by adapting the self-supervised learning mechanism to build source code model. The key novelty lies in training code representations by predicting automatically identified subtrees from the context of the ASTs. Subtrees in ASTs are treated with InferCode as the labels for training code representations without any human labeling effort or the overhead of expensive graph construction, and the trained representations are no longer tied to any specific downstream tasks or code units. We trained an InferCode model instance using the Tree-based CNN as the encoder of a large set of Java code and applied it to downstream unsupervised tasks such as code clustering, code clone detection, cross-language code search or reused under a transfer learning scheme to continue training the model weights for supervised tasks such as code classification and method name prediction. Compared to previous code learning techniques applied to the same downstream tasks, such as Code2Vec, Code2Seq, ASTNN, higher performance results are achieved using our pre-trained InferCode model with a significant margin for most tasks including those involving different programming languages. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.07023v2-abstract-full').style.display = 'none'; document.getElementById('2012.07023v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ICSE 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.09777">arXiv:2009.09777</a> <span> [<a href="https://arxiv.org/pdf/2009.09777">pdf</a>, <a href="https://arxiv.org/format/2009.09777">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> TreeCaps: Tree-Based Capsule Networks for Source Code Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bui%2C+N+D+Q">Nghi D. Q. Bui</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yijun Yu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+L">Lingxiao Jiang</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="2009.09777v4-abstract-short" style="display: inline;"> Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). Although graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code needs static code semantic analysis that may not be accurate and introduces… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.09777v4-abstract-full').style.display = 'inline'; document.getElementById('2009.09777v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.09777v4-abstract-full" style="display: none;"> Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). Although graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code needs static code semantic analysis that may not be accurate and introduces noise during learning. Although syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs, previous tree-based learning techniques have not been able to learn semantic information from trees to achieve better accuracy than graph-based techniques. We propose a new learning technique, named TreeCaps, by fusing together capsule networks with tree-based convolutional neural networks, to achieve learning accuracy higher than existing graph-based techniques while it is based only on trees. TreeCaps introduces novel variable-to-static routing algorithms into the capsule networks to compensate for the loss of previous routing algorithms. Aside from accuracy, we also find that TreeCaps is the most robust to withstand those semantic-preserving program transformations that change code syntax without modifying the semantics. Evaluated on a large number of Java and C/C++ programs, TreeCaps models outperform prior deep learning models of program source code, in terms of both accuracy and robustness for program comprehension tasks such as code functionality classification and function name prediction <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.09777v4-abstract-full').style.display = 'none'; document.getElementById('2009.09777v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at AAAI 2021</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=Bui%2C+N&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Bui%2C+N&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Bui%2C+N&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository