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 1,325 results for author: <span class="mathjax">Gao, J</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=Gao%2C+J">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="Gao, J"> </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=Gao%2C+J&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="Gao, J"> <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=Gao%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14385">arXiv:2411.14385</a> <span> [<a href="https://arxiv.org/pdf/2411.14385">pdf</a>, <a href="https://arxiv.org/format/2411.14385">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"> Enhancing Diagnostic Precision in Gastric Bleeding through Automated Lesion Segmentation: A Deep DuS-KFCM Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xian-Xian Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Mingkun Xu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yuanyuan Wei</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+H">Huafeng Qin</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Q">Qun Song</a>, <a href="/search/cs?searchtype=author&query=Fong%2C+S">Simon Fong</a>, <a href="/search/cs?searchtype=author&query=Tien%2C+F">Feng Tien</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+W">Wei Luo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Juntao Gao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhihua Zhang</a>, <a href="/search/cs?searchtype=author&query=Siu%2C+S">Shirley Siu</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="2411.14385v1-abstract-short" style="display: inline;"> Timely and precise classification and segmentation of gastric bleeding in endoscopic imagery are pivotal for the rapid diagnosis and intervention of gastric complications, which is critical in life-saving medical procedures. Traditional methods grapple with the challenge posed by the indistinguishable intensity values of bleeding tissues adjacent to other gastric structures. Our study seeks to rev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14385v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14385v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14385v1-abstract-full" style="display: none;"> Timely and precise classification and segmentation of gastric bleeding in endoscopic imagery are pivotal for the rapid diagnosis and intervention of gastric complications, which is critical in life-saving medical procedures. Traditional methods grapple with the challenge posed by the indistinguishable intensity values of bleeding tissues adjacent to other gastric structures. Our study seeks to revolutionize this domain by introducing a novel deep learning model, the Dual Spatial Kernelized Constrained Fuzzy C-Means (Deep DuS-KFCM) clustering algorithm. This Hybrid Neuro-Fuzzy system synergizes Neural Networks with Fuzzy Logic to offer a highly precise and efficient identification of bleeding regions. Implementing a two-fold coarse-to-fine strategy for segmentation, this model initially employs the Spatial Kernelized Fuzzy C-Means (SKFCM) algorithm enhanced with spatial intensity profiles and subsequently harnesses the state-of-the-art DeepLabv3+ with ResNet50 architecture to refine the segmentation output. Through extensive experiments across mainstream gastric bleeding and red spots datasets, our Deep DuS-KFCM model demonstrated unprecedented accuracy rates of 87.95%, coupled with a specificity of 96.33%, outperforming contemporary segmentation methods. The findings underscore the model's robustness against noise and its outstanding segmentation capabilities, particularly for identifying subtle bleeding symptoms, thereby presenting a significant leap forward in medical image processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14385v1-abstract-full').style.display = 'none'; document.getElementById('2411.14385v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14250">arXiv:2411.14250</a> <span> [<a href="https://arxiv.org/pdf/2411.14250">pdf</a>, <a href="https://arxiv.org/format/2411.14250">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"> CP-UNet: Contour-based Probabilistic Model for Medical Ultrasound Images Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+R">Ruiguo Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Y">Yuan Tian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiqiang Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xuewei Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jie Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.14250v1-abstract-short" style="display: inline;"> Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14250v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14250v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14250v1-abstract-full" style="display: none;"> Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, which guides the segmentation network to enhance its focus on contour during decoding. We design a novel down-sampling module to enable the contour probability distribution modeling and encoding stages to acquire global-local features. Furthermore, the Gaussian Mixture Model utilizes optimized features to model the contour distribution, capturing the uncertainty of lesion boundaries. Extensive experiments with several state-of-the-art deep learning segmentation methods on three ultrasound image datasets show that our method performs better on breast and thyroid lesions segmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14250v1-abstract-full').style.display = 'none'; document.getElementById('2411.14250v1-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 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">4 pages, 4 figures, 2 tables;For icassp2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13314">arXiv:2411.13314</a> <span> [<a href="https://arxiv.org/pdf/2411.13314">pdf</a>, <a href="https://arxiv.org/format/2411.13314">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> I2TTS: Image-indicated Immersive Text-to-speech Synthesis with Spatial Perception </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiawei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tian-Hao Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiaran Gao</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+X">Xinyuan Qian</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+X">Xu-Cheng Yin</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="2411.13314v1-abstract-short" style="display: inline;"> Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works have focused primarily on the technical aspects of producing natural-sounding speech, such as intonation, rhythm, and clarity. However, they overlook the fact that there is a growing emphasis on spatial perception of synthe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13314v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13314v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13314v1-abstract-full" style="display: none;"> Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works have focused primarily on the technical aspects of producing natural-sounding speech, such as intonation, rhythm, and clarity. However, they overlook the fact that there is a growing emphasis on spatial perception of synthesized speech, which may provide immersive experience in gaming and virtual reality. To solve this issue, in this paper, we present a novel multi-modal TTS approach, namely Image-indicated Immersive Text-to-speech Synthesis (I2TTS). Specifically, we introduce a scene prompt encoder that integrates visual scene prompts directly into the synthesis pipeline to control the speech generation process. Additionally, we propose a reverberation classification and refinement technique that adjusts the synthesized mel-spectrogram to enhance the immersive experience, ensuring that the involved reverberation condition matches the scene accurately. Experimental results demonstrate that our model achieves high-quality scene and spatial matching without compromising speech naturalness, marking a significant advancement in the field of context-aware speech synthesis. Project demo page: https://spatialTTS.github.io/ Index Terms-Speech synthesis, scene prompt, spatial perception <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13314v1-abstract-full').style.display = 'none'; document.getElementById('2411.13314v1-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 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">5pages,4figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12780">arXiv:2411.12780</a> <span> [<a href="https://arxiv.org/pdf/2411.12780">pdf</a>, <a href="https://arxiv.org/format/2411.12780">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"> Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+X">Xiuyuan Guo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chengqi Xu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+G">Guinan Guo</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+F">Feiyu Zhu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+C">Changpeng Cai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Peizhe Wang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+X">Xiaoming Wei</a>, <a href="/search/cs?searchtype=author&query=Su%2C+J">Junhao Su</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jialin Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12780v1-abstract-short" style="display: inline;"> Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and synchronization delays in traditional model parallelism methods, seamless parallel training cannot be achieved, which, to some extent, affects overall training efficiency. To address this issue, we present PPLL (Pipeline… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12780v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12780v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12780v1-abstract-full" style="display: none;"> Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and synchronization delays in traditional model parallelism methods, seamless parallel training cannot be achieved, which, to some extent, affects overall training efficiency. To address this issue, we present PPLL (Pipeline Parallelism based on Local Learning), a novel framework that leverages local learning algorithms to enable effective parallel training across multiple GPUs. PPLL divides the model into several distinct blocks, each allocated to a separate GPU. By utilizing queues to manage data transfers between GPUs, PPLL ensures seamless cross-GPU communication, allowing multiple blocks to execute forward and backward passes in a pipelined manner. This design minimizes idle times and prevents bottlenecks typically caused by sequential gradient updates, thereby accelerating the overall training process. We validate PPLL through extensive experiments using ResNet and Vision Transformer (ViT) architectures on CIFAR-10, SVHN, and STL-10 datasets. Our results demonstrate that PPLL significantly enhances the training speed of the local learning method while achieving comparable or even superior training speed to traditional pipeline parallelism (PP) without sacrificing model performance. In a 4-GPU training setup, PPLL accelerated local learning training on ViT and ResNet by 162% and 33%, respectively, achieving 1.25x and 0.85x the speed of traditional pipeline parallelism. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12780v1-abstract-full').style.display = 'none'; document.getElementById('2411.12780v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12229">arXiv:2411.12229</a> <span> [<a href="https://arxiv.org/pdf/2411.12229">pdf</a>, <a href="https://arxiv.org/format/2411.12229">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <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"> SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gou%2C+Y">Yutong Gou</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianyang Gao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yuexuan Xu</a>, <a href="/search/cs?searchtype=author&query=Long%2C+C">Cheng Long</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="2411.12229v1-abstract-short" style="display: inline;"> Approximate nearest neighbor (ANN) search in high-dimensional Euclidean space has a broad range of applications. Among existing ANN algorithms, graph-based methods have shown superior performance in terms of the time-accuracy trade-off. However, they face performance bottlenecks due to the random memory accesses caused by the searching process on the graph indices and the costs of computing exact… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12229v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12229v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12229v1-abstract-full" style="display: none;"> Approximate nearest neighbor (ANN) search in high-dimensional Euclidean space has a broad range of applications. Among existing ANN algorithms, graph-based methods have shown superior performance in terms of the time-accuracy trade-off. However, they face performance bottlenecks due to the random memory accesses caused by the searching process on the graph indices and the costs of computing exact distances to guide the searching process. To relieve the bottlenecks, a recent method named NGT-QG makes an attempt by integrating quantization and graph. It (1) replicates and stores the quantization codes of a vertex's neighbors compactly so that they can be accessed sequentially, and (2) uses a SIMD-based implementation named FastScan to efficiently estimate distances based on the quantization codes in batch for guiding the searching process. While NGT-QG achieves promising improvements over the vanilla graph-based methods, it has not fully unleashed the potential of integrating quantization and graph. For instance, it entails a re-ranking step to compute exact distances at the end, which introduces extra random memory accesses; its graph structure is not jointly designed considering the in-batch nature of FastScan, which causes wastes of computation in searching. In this work, following NGT-QG, we present a new method named SymphonyQG, which achieves more symphonious integration of quantization and graph (e.g., it avoids the explicit re-ranking step and refines the graph structure to be more aligned with FastScan). Based on extensive experiments on real-world datasets, SymphonyQG establishes the new state-of-the-art in terms of the time-accuracy trade-off. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12229v1-abstract-full').style.display = 'none'; document.getElementById('2411.12229v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The paper has been accepted by SIGMOD 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/2411.12222">arXiv:2411.12222</a> <span> [<a href="https://arxiv.org/pdf/2411.12222">pdf</a>, <a href="https://arxiv.org/format/2411.12222">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"> Contrast Similarity-Aware Dual-Pathway Mamba for Multivariate Time Series Node Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Du%2C+M">Mingsen Du</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+M">Meng Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yongjian Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiuxin Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiahui Gao</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+C">Cun Ji</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+S">Shoushui Wei</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="2411.12222v1-abstract-short" style="display: inline;"> Multivariate time series (MTS) data is generated through multiple sensors across various domains such as engineering application, health monitoring, and the internet of things, characterized by its temporal changes and high dimensional characteristics. Over the past few years, many studies have explored the long-range dependencies and similarities in MTS. However, long-range dependencies are diffi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12222v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12222v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12222v1-abstract-full" style="display: none;"> Multivariate time series (MTS) data is generated through multiple sensors across various domains such as engineering application, health monitoring, and the internet of things, characterized by its temporal changes and high dimensional characteristics. Over the past few years, many studies have explored the long-range dependencies and similarities in MTS. However, long-range dependencies are difficult to model due to their temporal changes and high dimensionality makes it difficult to obtain similarities effectively and efficiently. Thus, to address these issues, we propose contrast similarity-aware dual-pathway Mamba for MTS node classification (CS-DPMamba). Firstly, to obtain the dynamic similarity of each sample, we initially use temporal contrast learning module to acquire MTS representations. And then we construct a similarity matrix between MTS representations using Fast Dynamic Time Warping (FastDTW). Secondly, we apply the DPMamba to consider the bidirectional nature of MTS, allowing us to better capture long-range and short-range dependencies within the data. Finally, we utilize the Kolmogorov-Arnold Network enhanced Graph Isomorphism Network to complete the information interaction in the matrix and MTS node classification task. By comprehensively considering the long-range dependencies and dynamic similarity features, we achieved precise MTS node classification. We conducted experiments on multiple University of East Anglia (UEA) MTS datasets, which encompass diverse application scenarios. Our results demonstrate the superiority of our method through both supervised and semi-supervised experiments on the MTS classification task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12222v1-abstract-full').style.display = 'none'; document.getElementById('2411.12222v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to Knowledge-Based Systems on Nov 17, 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/2411.11507">arXiv:2411.11507</a> <span> [<a href="https://arxiv.org/pdf/2411.11507">pdf</a>, <a href="https://arxiv.org/format/2411.11507">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"> SignEye: Traffic Sign Interpretation from Vehicle First-Person View </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chuang Yang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+X">Xu Han</a>, <a href="/search/cs?searchtype=author&query=Han%2C+T">Tao Han</a>, <a href="/search/cs?searchtype=author&query=SU%2C+Y">Yuejiao SU</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyu Gao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hongyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yi Wang</a>, <a href="/search/cs?searchtype=author&query=Chau%2C+L">Lap-Pui Chau</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="2411.11507v1-abstract-short" style="display: inline;"> Traffic signs play a key role in assisting autonomous driving systems (ADS) by enabling the assessment of vehicle behavior in compliance with traffic regulations and providing navigation instructions. However, current works are limited to basic sign understanding without considering the egocentric vehicle's spatial position, which fails to support further regulation assessment and direction naviga… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11507v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11507v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11507v1-abstract-full" style="display: none;"> Traffic signs play a key role in assisting autonomous driving systems (ADS) by enabling the assessment of vehicle behavior in compliance with traffic regulations and providing navigation instructions. However, current works are limited to basic sign understanding without considering the egocentric vehicle's spatial position, which fails to support further regulation assessment and direction navigation. Following the above issues, we introduce a new task: traffic sign interpretation from the vehicle's first-person view, referred to as TSI-FPV. Meanwhile, we develop a traffic guidance assistant (TGA) scenario application to re-explore the role of traffic signs in ADS as a complement to popular autonomous technologies (such as obstacle perception). Notably, TGA is not a replacement for electronic map navigation; rather, TGA can be an automatic tool for updating it and complementing it in situations such as offline conditions or temporary sign adjustments. Lastly, a spatial and semantic logic-aware stepwise reasoning pipeline (SignEye) is constructed to achieve the TSI-FPV and TGA, and an application-specific dataset (Traffic-CN) is built. Experiments show that TSI-FPV and TGA are achievable via our SignEye trained on Traffic-CN. The results also demonstrate that the TGA can provide complementary information to ADS beyond existing popular autonomous technologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11507v1-abstract-full').style.display = 'none'; document.getElementById('2411.11507v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11284">arXiv:2411.11284</a> <span> [<a href="https://arxiv.org/pdf/2411.11284">pdf</a>, <a href="https://arxiv.org/format/2411.11284">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"> Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yachao Yang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yanfeng Sun</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jipeng Guo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junbin Gao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shaofan Wang</a>, <a href="/search/cs?searchtype=author&query=Ju%2C+F">Fujiao Ju</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+B">Baocai Yin</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="2411.11284v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node representations, and the low-pass filtering nature of most GNNs leading to the oversight of valuable high-frequency information in graph signals. These issues are particular… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11284v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11284v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11284v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node representations, and the low-pass filtering nature of most GNNs leading to the oversight of valuable high-frequency information in graph signals. These issues are particularly pronounced in heterophilic graphs. To address these challenges, we propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN). DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features, using frequency-specific constraints to minimize noise and redundancy in the respective frequency bands. The model dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs. Furthermore, DFGNN mitigates interference by aligning topological and attribute representations through dynamic correspondences between their respective frequency bands, enhancing overall model performance and expressiveness. Extensive experiments conducted on benchmark datasets demonstrate that DFGNN outperforms state-of-the-art methods in classification performance, highlighting its effectiveness in handling both homophilic and heterophilic graphs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11284v1-abstract-full').style.display = 'none'; document.getElementById('2411.11284v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 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">11pages,17figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11069">arXiv:2411.11069</a> <span> [<a href="https://arxiv.org/pdf/2411.11069">pdf</a>, <a href="https://arxiv.org/format/2411.11069">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"> Skeleton-Guided Spatial-Temporal Feature Learning for Video-Based Visible-Infrared Person Re-Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wenjia Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xiaoke Zhu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiakang Gao</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+D">Di Liao</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="2411.11069v1-abstract-short" style="display: inline;"> Video-based visible-infrared person re-identification (VVI-ReID) is challenging due to significant modality feature discrepancies. Spatial-temporal information in videos is crucial, but the accuracy of spatial-temporal information is often influenced by issues like low quality and occlusions in videos. Existing methods mainly focus on reducing modality differences, but pay limited attention to imp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11069v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11069v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11069v1-abstract-full" style="display: none;"> Video-based visible-infrared person re-identification (VVI-ReID) is challenging due to significant modality feature discrepancies. Spatial-temporal information in videos is crucial, but the accuracy of spatial-temporal information is often influenced by issues like low quality and occlusions in videos. Existing methods mainly focus on reducing modality differences, but pay limited attention to improving spatial-temporal features, particularly for infrared videos. To address this, we propose a novel Skeleton-guided spatial-Temporal feAture leaRning (STAR) method for VVI-ReID. By using skeleton information, which is robust to issues such as poor image quality and occlusions, STAR improves the accuracy of spatial-temporal features in videos of both modalities. Specifically, STAR employs two levels of skeleton-guided strategies: frame level and sequence level. At the frame level, the robust structured skeleton information is used to refine the visual features of individual frames. At the sequence level, we design a feature aggregation mechanism based on skeleton key points graph, which learns the contribution of different body parts to spatial-temporal features, further enhancing the accuracy of global features. Experiments on benchmark datasets demonstrate that STAR outperforms state-of-the-art methods. Code will be open source soon. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11069v1-abstract-full').style.display = 'none'; document.getElementById('2411.11069v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10889">arXiv:2411.10889</a> <span> [<a href="https://arxiv.org/pdf/2411.10889">pdf</a>, <a href="https://arxiv.org/format/2411.10889">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deng%2C+C">Chengyuan Deng</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jie Gao</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+K">Kevin Lu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+F">Feng Luo</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Hongbin Sun</a>, <a href="/search/cs?searchtype=author&query=Xin%2C+C">Cheng Xin</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="2411.10889v1-abstract-short" style="display: inline;"> We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10889v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10889v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10889v1-abstract-full" style="display: none;"> We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10889v1-abstract-full').style.display = 'none'; document.getElementById('2411.10889v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to 38th Conference on Neural Information Processing Systems (NeurIPS 2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10143">arXiv:2411.10143</a> <span> [<a href="https://arxiv.org/pdf/2411.10143">pdf</a>, <a href="https://arxiv.org/format/2411.10143">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mathematical Software">cs.MS</span> </div> </div> <p class="title is-5 mathjax"> Cascaded Prediction and Asynchronous Execution of Iterative Algorithms on Heterogeneous Platforms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianhua Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bingjie Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yizhuo Wang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+W">Weixing Ji</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hua Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10143v1-abstract-short" style="display: inline;"> Owing to the diverse scales and varying distributions of sparse matrices arising from practical problems, a multitude of choices are present in the design and implementation of sparse matrix-vector multiplication (SpMV). Researchers have proposed many machine learning-based optimization methods for SpMV. However, these efforts only support one area of sparse matrix format selection, SpMV algorithm… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10143v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10143v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10143v1-abstract-full" style="display: none;"> Owing to the diverse scales and varying distributions of sparse matrices arising from practical problems, a multitude of choices are present in the design and implementation of sparse matrix-vector multiplication (SpMV). Researchers have proposed many machine learning-based optimization methods for SpMV. However, these efforts only support one area of sparse matrix format selection, SpMV algorithm selection, or parameter configuration, and rarely consider a large amount of time overhead associated with feature extraction, model inference, and compression format conversion. This paper introduces a machine learning-based cascaded prediction method for SpMV computations that spans various computing stages and hierarchies. Besides, an asynchronous and concurrent computing model has been designed and implemented for runtime model prediction and iterative algorithm solving on heterogeneous computing platforms. It not only offers comprehensive support for the iterative algorithm-solving process leveraging machine learning technology, but also effectively mitigates the preprocessing overheads. Experimental results demonstrate that the cascaded prediction introduced in this paper accelerates SpMV by 1.33x on average, and the iterative algorithm, enhanced by cascaded prediction and asynchronous execution, optimizes by 2.55x on average. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10143v1-abstract-full').style.display = 'none'; document.getElementById('2411.10143v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 9 figures, 7 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-02; 68W10; 65F50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> A.1; D.1.3; G.1.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09639">arXiv:2411.09639</a> <span> [<a href="https://arxiv.org/pdf/2411.09639">pdf</a>, <a href="https://arxiv.org/format/2411.09639">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"> MCCE: Missingness-aware Causal Concept Explainer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jifan Gao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">Guanhua Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09639v1-abstract-short" style="display: inline;"> Causal concept effect estimation is gaining increasing interest in the field of interpretable machine learning. This general approach explains the behaviors of machine learning models by estimating the causal effect of human-understandable concepts, which represent high-level knowledge more comprehensibly than raw inputs like tokens. However, existing causal concept effect explanation methods assu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09639v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09639v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09639v1-abstract-full" style="display: none;"> Causal concept effect estimation is gaining increasing interest in the field of interpretable machine learning. This general approach explains the behaviors of machine learning models by estimating the causal effect of human-understandable concepts, which represent high-level knowledge more comprehensibly than raw inputs like tokens. However, existing causal concept effect explanation methods assume complete observation of all concepts involved within the dataset, which can fail in practice due to incomplete annotations or missing concept data. We theoretically demonstrate that unobserved concepts can bias the estimation of the causal effects of observed concepts. To address this limitation, we introduce the Missingness-aware Causal Concept Explainer (MCCE), a novel framework specifically designed to estimate causal concept effects when not all concepts are observable. Our framework learns to account for residual bias resulting from missing concepts and utilizes a linear predictor to model the relationships between these concepts and the outputs of black-box machine learning models. It can offer explanations on both local and global levels. We conduct validations using a real-world dataset, demonstrating that MCCE achieves promising performance compared to state-of-the-art explanation methods in causal concept effect estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09639v1-abstract-full').style.display = 'none'; document.getElementById('2411.09639v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09289">arXiv:2411.09289</a> <span> [<a href="https://arxiv.org/pdf/2411.09289">pdf</a>, <a href="https://arxiv.org/format/2411.09289">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"> StreamAdapter: Efficient Test Time Adaptation from Contextual Streams </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Muhtar%2C+D">Dilxat Muhtar</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yelong Shen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yaming Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaodong Liu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yadong Lu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jianfeng Liu</a>, <a href="/search/cs?searchtype=author&query=Zhan%2C+Y">Yuefeng Zhan</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Hao Sun</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+W">Weiwei Deng</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+F">Feng Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xueliang Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weizhu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09289v1-abstract-short" style="display: inline;"> In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances have expanded context windows to accommodate more demonstrations, this approach increases inference costs without necessarily improving performance. To mitigate these issues, We propose StreamAdapter, a novel approach t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09289v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09289v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09289v1-abstract-full" style="display: none;"> In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances have expanded context windows to accommodate more demonstrations, this approach increases inference costs without necessarily improving performance. To mitigate these issues, We propose StreamAdapter, a novel approach that directly updates model parameters from context at test time, eliminating the need for explicit in-context demonstrations. StreamAdapter employs context mapping and weight absorption mechanisms to dynamically transform ICL demonstrations into parameter updates with minimal additional parameters. By reducing reliance on numerous in-context examples, StreamAdapter significantly reduce inference costs and allows for efficient inference with constant time complexity, regardless of demonstration count. Extensive experiments across diverse tasks and model architectures demonstrate that StreamAdapter achieves comparable or superior adaptation capability to ICL while requiring significantly fewer demonstrations. The superior task adaptation and context encoding capabilities of StreamAdapter on both language understanding and generation tasks provides a new perspective for adapting LLMs at test time using context, allowing for more efficient adaptation across scenarios and more cost-effective inference <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09289v1-abstract-full').style.display = 'none'; document.getElementById('2411.09289v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 Pages, 9 Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08896">arXiv:2411.08896</a> <span> [<a href="https://arxiv.org/pdf/2411.08896">pdf</a>, <a href="https://arxiv.org/format/2411.08896">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Demand-Aware Beam Hopping and Power Allocation for Load Balancing in Digital Twin empowered LEO Satellite Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+R">Ruili Zhao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+J">Jun Cai</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+J">Jiangtao Luo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junpeng Gao</a>, <a href="/search/cs?searchtype=author&query=Ran%2C+Y">Yongyi Ran</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="2411.08896v1-abstract-short" style="display: inline;"> Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. However, the uneven geographical distribution and temporal variability of ground traffic demands, combined with the high mobility of LEO satellites, present significant challenges for efficient beam resource utilization. Traditional BH methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08896v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08896v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08896v1-abstract-full" style="display: none;"> Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. However, the uneven geographical distribution and temporal variability of ground traffic demands, combined with the high mobility of LEO satellites, present significant challenges for efficient beam resource utilization. Traditional BH methods based on GEO satellites fail to address issues such as satellite interference, overlapping coverage, and mobility. This paper explores a Digital Twin (DT)-based collaborative resource allocation network for multiple LEO satellites with overlapping coverage areas. A two-tier optimization problem, focusing on load balancing and cell service fairness, is proposed to maximize throughput and minimize inter-cell service delay. The DT layer optimizes the allocation of overlapping coverage cells by designing BH patterns for each satellite, while the LEO layer optimizes power allocation for each selected service cell. At the DT layer, an Actor-Critic network is deployed on each agent, with a global critic network in the cloud center. The A3C algorithm is employed to optimize the DT layer. Concurrently, the LEO layer optimization is performed using a Multi-Agent Reinforcement Learning algorithm, where each beam functions as an independent agent. The simulation results show that this method reduces satellite load disparity by about 72.5% and decreases the average delay to 12ms. Additionally, our approach outperforms other benchmarks in terms of throughput, ensuring a better alignment between offered and requested data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08896v1-abstract-full').style.display = 'none'; document.getElementById('2411.08896v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08599">arXiv:2411.08599</a> <span> [<a href="https://arxiv.org/pdf/2411.08599">pdf</a>, <a href="https://arxiv.org/format/2411.08599">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</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"> XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yingqi Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yifu Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoxia Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xiaorong Shi</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yin Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yiming Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shiqi Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wei Li</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+Y">Yuntao Hong</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Zhiling Luo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jinyang Gao</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Liyu Mou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yu Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08599v1-abstract-short" style="display: inline;"> To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of gen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08599v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08599v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08599v1-abstract-full" style="display: none;"> To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of training strategies to fine-tune models to generate high-quality candidates with diverse preferences. On the other hand, we implement the ICL approach with an example selection method based on named entity recognition to prevent overemphasis on entities. The refiner optimizes each candidate by correcting logical or syntactical errors. To address the challenge of identifying the best candidate, we fine-tune a selection model to distinguish nuances of candidate SQL queries. The experimental results on multiple dialect datasets demonstrate the robustness of XiYan-SQL in addressing challenges across different scenarios. Overall, our proposed XiYan-SQL achieves the state-of-the-art execution accuracy of 89.65% on the Spider test set, 69.86% on SQL-Eval, 41.20% on NL2GQL, and a competitive score of 72.23% on the Bird development benchmark. The proposed framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08599v1-abstract-full').style.display = 'none'; document.getElementById('2411.08599v1-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 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">ACM Class:</span> I.2; H.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08561">arXiv:2411.08561</a> <span> [<a href="https://arxiv.org/pdf/2411.08561">pdf</a>, <a href="https://arxiv.org/format/2411.08561">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"> LogLLM: Log-based Anomaly Detection Using Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guan%2C+W">Wei Guan</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jian Cao</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+S">Shiyou Qian</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianqi Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08561v1-abstract-short" style="display: inline;"> Software systems often record important runtime information in logs to help with troubleshooting. Log-based anomaly detection has become a key research area that aims to identify system issues through log data, ultimately enhancing the reliability of software systems. Traditional deep learning methods often struggle to capture the semantic information embedded in log data, which is typically organ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08561v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08561v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08561v1-abstract-full" style="display: none;"> Software systems often record important runtime information in logs to help with troubleshooting. Log-based anomaly detection has become a key research area that aims to identify system issues through log data, ultimately enhancing the reliability of software systems. Traditional deep learning methods often struggle to capture the semantic information embedded in log data, which is typically organized in natural language. In this paper, we propose LogLLM, a log-based anomaly detection framework that leverages large language models (LLMs). LogLLM employs BERT for extracting semantic vectors from log messages, while utilizing Llama, a transformer decoder-based model, for classifying log sequences. Additionally, we introduce a projector to align the vector representation spaces of BERT and Llama, ensuring a cohesive understanding of log semantics. Unlike conventional methods that require log parsers to extract templates, LogLLM preprocesses log messages with regular expressions, streamlining the entire process. Our framework is trained through a novel three-stage procedure designed to enhance performance and adaptability. Experimental results across four public datasets demonstrate that LogLLM outperforms state-of-the-art methods. Even when handling unstable logs, it effectively captures the semantic meaning of log messages and detects anomalies accurately. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08561v1-abstract-full').style.display = 'none'; document.getElementById('2411.08561v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07751">arXiv:2411.07751</a> <span> [<a href="https://arxiv.org/pdf/2411.07751">pdf</a>, <a href="https://arxiv.org/format/2411.07751">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qian%2C+X">Xinyuan Qian</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiaran Gao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yaodan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qiquan Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hexin Liu</a>, <a href="/search/cs?searchtype=author&query=Garcia%2C+L+P">Leibny Paola Garcia</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haizhou Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07751v1-abstract-short" style="display: inline;"> Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07751v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07751v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07751v1-abstract-full" style="display: none;"> Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas contextual visual cues from the surrounding environment have been overlooked: for example, when we see a dog bark, our brain has the innate ability to discern and filter out the barking noise. To this end, in this paper, we introduce a novel task, i.e. SAV-SE. To our best knowledge, this is the first proposal to use rich contextual information from synchronized video as auxiliary cues to indicate the type of noise, which eventually improves the speech enhancement performance. Specifically, we propose the VC-S$^2$E method, which incorporates the Conformer and Mamba modules for their complementary strengths. Extensive experiments are conducted on public MUSIC, AVSpeech and AudioSet datasets, where the results demonstrate the superiority of VC-S$^2$E over other competitive methods. We will make the source code publicly available. Project demo page: https://AVSEPage.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07751v1-abstract-full').style.display = 'none'; document.getElementById('2411.07751v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06780">arXiv:2411.06780</a> <span> [<a href="https://arxiv.org/pdf/2411.06780">pdf</a>, <a href="https://arxiv.org/format/2411.06780">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"> HSTrack: Bootstrap End-to-End Multi-Camera 3D Multi-object Tracking with Hybrid Supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+S">Shubo Lin</a>, <a href="/search/cs?searchtype=author&query=Kou%2C+Y">Yutong Kou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bing Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+W">Weiming Hu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jin Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06780v1-abstract-short" style="display: inline;"> In camera-based 3D multi-object tracking (MOT), the prevailing methods follow the tracking-by-query-propagation paradigm, which employs track queries to manage the lifecycle of identity-consistent tracklets while object queries handle the detection of new-born tracklets. However, this intertwined paradigm leads the inter-temporal tracking task and the single-frame detection task utilize the same m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06780v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06780v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06780v1-abstract-full" style="display: none;"> In camera-based 3D multi-object tracking (MOT), the prevailing methods follow the tracking-by-query-propagation paradigm, which employs track queries to manage the lifecycle of identity-consistent tracklets while object queries handle the detection of new-born tracklets. However, this intertwined paradigm leads the inter-temporal tracking task and the single-frame detection task utilize the same model parameters, complicating training optimization. Drawing inspiration from studies on the roles of attention components in transformer-based decoders, we identify that the dispersing effect of self-attention necessitates object queries to match with new-born tracklets. This matching strategy diverges from the detection pre-training phase, where object queries align with all ground-truth targets, resulting in insufficient supervision signals. To address these issues, we present HSTrack, a novel plug-and-play method designed to co-facilitate multi-task learning for detection and tracking. HSTrack constructs a parallel weight-share decoder devoid of self-attention layers, circumventing competition between different types of queries. Considering the characteristics of cross-attention layer and distinct query types, our parallel decoder adopt one-to-one and one-to-many label assignment strategies for track queries and object queries, respectively. Leveraging the shared architecture, HSTrack further improve trackers for spatio-temporal modeling and quality candidates generation. Extensive experiments demonstrate that HSTrack consistently delivers improvements when integrated with various query-based 3D MOT trackers. For example, HSTrack improves the state-of-the-art PF-Track method by $+2.3\%$ AMOTA and $+1.7\%$ mAP on the nuScenes dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06780v1-abstract-full').style.display = 'none'; document.getElementById('2411.06780v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <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, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06659">arXiv:2411.06659</a> <span> [<a href="https://arxiv.org/pdf/2411.06659">pdf</a>, <a href="https://arxiv.org/format/2411.06659">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"> An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+D">Dong Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Aijia Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junqi Gao</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+B">Biqing Qi</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="2411.06659v1-abstract-short" style="display: inline;"> Incremental graph learning has gained significant attention for its ability to address the catastrophic forgetting problem in graph representation learning. However, traditional methods often rely on a large number of labels for node classification, which is impractical in real-world applications. This makes few-shot incremental learning on graphs a pressing need. Current methods typically require… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06659v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06659v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06659v1-abstract-full" style="display: none;"> Incremental graph learning has gained significant attention for its ability to address the catastrophic forgetting problem in graph representation learning. However, traditional methods often rely on a large number of labels for node classification, which is impractical in real-world applications. This makes few-shot incremental learning on graphs a pressing need. Current methods typically require extensive training samples from meta-learning to build memory and perform intensive fine-tuning of GNN parameters, leading to high memory consumption and potential loss of previously learned knowledge. To tackle these challenges, we introduce Mecoin, an efficient method for building and maintaining memory. Mecoin employs Structured Memory Units to cache prototypes of learned categories, as well as Memory Construction Modules to update these prototypes for new categories through interactions between the nodes and the cached prototypes. Additionally, we have designed a Memory Representation Adaptation Module to store probabilities associated with each class prototype, reducing the need for parameter fine-tuning and lowering the forgetting rate. When a sample matches its corresponding class prototype, the relevant probabilities are retrieved from the MRaM. Knowledge is then distilled back into the GNN through a Graph Knowledge Distillation Module, preserving the model's memory. We analyze the effectiveness of Mecoin in terms of generalization error and explore the impact of different distillation strategies on model performance through experiments and VC-dimension analysis. Compared to other related works, Mecoin shows superior performance in accuracy and forgetting rate. Our code is publicly available on the https://github.com/Arvin0313/Mecoin-GFSCIL.git . <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06659v1-abstract-full').style.display = 'none'; document.getElementById('2411.06659v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 6 figures, 38th Conference on Neural Information Processing Systems, 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/2411.05877">arXiv:2411.05877</a> <span> [<a href="https://arxiv.org/pdf/2411.05877">pdf</a>, <a href="https://arxiv.org/format/2411.05877">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tong Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+H">Hao Fang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+P">Patrick Xia</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaodong Liu</a>, <a href="/search/cs?searchtype=author&query=Van+Durme%2C+B">Benjamin Van Durme</a>, <a href="/search/cs?searchtype=author&query=Zettlemoyer%2C+L">Luke Zettlemoyer</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+H">Hao Cheng</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="2411.05877v1-abstract-short" style="display: inline;"> Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning incurs significant training cost and prompting increases inference overhead. We introduce $GenerativeAdapter$, an effective and efficient adaptation method that di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05877v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05877v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05877v1-abstract-full" style="display: none;"> Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning incurs significant training cost and prompting increases inference overhead. We introduce $GenerativeAdapter$, an effective and efficient adaptation method that directly maps new contexts to low-rank LM adapters, thereby significantly reducing inference overhead with no need for finetuning. The adapter generator is trained via self-supervised learning, and can be used to adapt a single frozen LM for any new task simply by mapping the associated task or domain context to a new adapter. We apply $GenerativeAdapter$ to two pretrained LMs (Mistral-7B-Instruct and Llama2-7B-Chat) and evaluate the adapted models in three adaption scenarios: knowledge acquisition from documents, learning from demonstrations, and personalization for users. In StreamingQA, our approach is effective in injecting knowledge into the LM's parameters, achieving a 63.5% improvement in F1 score over the model with supervised fine-tuning (from $19.5$ to $31.5$) for contexts as long as 32K tokens. In the MetaICL in-context learning evaluation, our method achieves an average accuracy of $44.9$ across 26 tasks, outperforming the base model. On MSC, our method proves to be highly competitive in memorizing user information from conversations with a 4x reduction in computation and memory costs compared to prompting with full conversation history. Together, these results suggest that $GenerativeAdapter$ should allow for general adaption to a wide range of different contexts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05877v1-abstract-full').style.display = 'none'; document.getElementById('2411.05877v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04936">arXiv:2411.04936</a> <span> [<a href="https://arxiv.org/pdf/2411.04936">pdf</a>, <a href="https://arxiv.org/format/2411.04936">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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Fed-LDR: Federated Local Data-infused Graph Creation with Node-centric Model Refinement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiechao Gao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuangang Li</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+S+F">Syeda Faiza Ahmed</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="2411.04936v1-abstract-short" style="display: inline;"> The rapid acceleration of global urbanization has introduced novel challenges in enhancing urban infrastructure and services. Spatio-temporal data, integrating spatial and temporal dimensions, has emerged as a critical tool for understanding urban phenomena and promoting sustainability. In this context, Federated Learning (FL) has gained prominence as a distributed learning paradigm aligned with t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04936v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04936v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04936v1-abstract-full" style="display: none;"> The rapid acceleration of global urbanization has introduced novel challenges in enhancing urban infrastructure and services. Spatio-temporal data, integrating spatial and temporal dimensions, has emerged as a critical tool for understanding urban phenomena and promoting sustainability. In this context, Federated Learning (FL) has gained prominence as a distributed learning paradigm aligned with the privacy requirements of urban IoT environments. However, integrating traditional and deep learning models into the FL framework poses significant challenges, particularly in capturing complex spatio-temporal dependencies and adapting to diverse urban conditions. To address these challenges, we propose the Federated Local Data-Infused Graph Creation with Node-centric Model Refinement (Fed-LDR) algorithm. Fed-LDR leverages FL and Graph Convolutional Networks (GCN) to enhance spatio-temporal data analysis in urban environments. The algorithm comprises two key modules: (1) the Local Data-Infused Graph Creation (LDIGC) module, which dynamically reconfigures adjacency matrices to reflect evolving spatial relationships within urban environments, and (2) the Node-centric Model Refinement (NoMoR) module, which customizes model parameters for individual urban nodes to accommodate heterogeneity. Evaluations on the PeMSD4 and PeMSD8 datasets demonstrate Fed-LDR's superior performance over six baseline methods. Fed-LDR achieved the lowest Mean Absolute Error (MAE) values of 20.15 and 17.30, and the lowest Root Mean Square Error (RMSE) values of 32.30 and 27.15, respectively, while maintaining a high correlation coefficient of 0.96 across both datasets. Notably, on the PeMSD4 dataset, Fed-LDR reduced MAE and RMSE by up to 81\% and 78\%, respectively, compared to the best-performing baseline FedMedian. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04936v1-abstract-full').style.display = 'none'; document.getElementById('2411.04936v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04686">arXiv:2411.04686</a> <span> [<a href="https://arxiv.org/pdf/2411.04686">pdf</a>, <a href="https://arxiv.org/format/2411.04686">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> Precision-Aware Iterative Algorithms Based on Group-Shared Exponents of Floating-Point Numbers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianhua Gao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+J">Jiayuan Shen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+W">Weixing Ji</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hua Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04686v1-abstract-short" style="display: inline;"> Iterative solvers are frequently used in scientific applications and engineering computations. However, the memory-bound Sparse Matrix-Vector (SpMV) kernel computation hinders the efficiency of iterative algorithms. As modern hardware increasingly supports low-precision computation, the mixed-precision optimization of iterative algorithms has garnered widespread attention. Nevertheless, existing m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04686v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04686v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04686v1-abstract-full" style="display: none;"> Iterative solvers are frequently used in scientific applications and engineering computations. However, the memory-bound Sparse Matrix-Vector (SpMV) kernel computation hinders the efficiency of iterative algorithms. As modern hardware increasingly supports low-precision computation, the mixed-precision optimization of iterative algorithms has garnered widespread attention. Nevertheless, existing mixed-precision methods pose challenges, including format conversion overhead, tight coupling between storage and computation representation, and the need to store multiple precision copies of data. This paper proposes a floating-point representation based on the group-shared exponent and segmented storage of the mantissa, enabling higher bit utilization of the representation vector and fast switches between different precisions without needing multiple data copies. Furthermore, a stepped mixed-precision iterative algorithm is proposed. Our experimental results demonstrate that, compared with existing floating-point formats, our approach significantly improves iterative algorithms' performance and convergence residuals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04686v1-abstract-full').style.display = 'none'; document.getElementById('2411.04686v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 9 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-02; 68W10; 65F50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> A.1; D.1.3; G.1.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03294">arXiv:2411.03294</a> <span> [<a href="https://arxiv.org/pdf/2411.03294">pdf</a>, <a href="https://arxiv.org/format/2411.03294">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy For Visuomotor Imitation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+G+J">George Jiayuan Gao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tianyu Li</a>, <a href="/search/cs?searchtype=author&query=Figueroa%2C+N">Nadia Figueroa</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="2411.03294v2-abstract-short" style="display: inline;"> We propose an object-centric recovery policy framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning. Previous behavior cloning (BC) methods rely heavily on a large amount of labeled data coverage, failing in unfamiliar spatial states. Without relying on extra data collection, our approach learns a recovery policy constructed by an inverse policy in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03294v2-abstract-full').style.display = 'inline'; document.getElementById('2411.03294v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03294v2-abstract-full" style="display: none;"> We propose an object-centric recovery policy framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning. Previous behavior cloning (BC) methods rely heavily on a large amount of labeled data coverage, failing in unfamiliar spatial states. Without relying on extra data collection, our approach learns a recovery policy constructed by an inverse policy inferred from object keypoint manifold gradient in the original training data. The recovery policy serves as a simple add-on to any base visuomotor BC policy, agnostic to a specific method, guiding the system back towards the training distribution to ensure task success even in OOD situations. We demonstrate the effectiveness of our object-centric framework in both simulation and real robot experiments, achieving an improvement of 77.7% over the base policy in OOD. Project Website: https://sites.google.com/view/ocr-penn <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03294v2-abstract-full').style.display = 'none'; document.getElementById('2411.03294v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for Spotlight (5 out of 21 papers) at CoRL 2024 Workshop on Lifelong Learning for Home Robots</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02794">arXiv:2411.02794</a> <span> [<a href="https://arxiv.org/pdf/2411.02794">pdf</a>, <a href="https://arxiv.org/format/2411.02794">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+X">Xu Han</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyu Gao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chuang Yang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+Y">Yuan Yuan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qi Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02794v1-abstract-short" style="display: inline;"> Texts on the intelligent transportation scene include mass information. Fully harnessing this information is one of the critical drivers for advancing intelligent transportation. Unlike the general scene, detecting text in transportation has extra demand, such as a fast inference speed, except for high accuracy. Most existing real-time text detection methods are based on the shrink mask, which los… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02794v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02794v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02794v1-abstract-full" style="display: none;"> Texts on the intelligent transportation scene include mass information. Fully harnessing this information is one of the critical drivers for advancing intelligent transportation. Unlike the general scene, detecting text in transportation has extra demand, such as a fast inference speed, except for high accuracy. Most existing real-time text detection methods are based on the shrink mask, which loses some geometry semantic information and needs complex post-processing. In addition, the previous method usually focuses on correct output, which ignores feature correction and lacks guidance during the intermediate process. To this end, we propose an efficient multi-scene text detector that contains an effective text representation similar mask (SM) and a feature correction module (FCM). Unlike previous methods, the former aims to preserve the geometric information of the instances as much as possible. Its post-progressing saves 50$\%$ of the time, accurately and efficiently reconstructing text contours. The latter encourages false positive features to move away from the positive feature center, optimizing the predictions from the feature level. Some ablation studies demonstrate the efficiency of the SM and the effectiveness of the FCM. Moreover, the deficiency of existing traffic datasets (such as the low-quality annotation or closed source data unavailability) motivated us to collect and annotate a traffic text dataset, which introduces motion blur. In addition, to validate the scene robustness of the SM-Net, we conduct experiments on traffic, industrial, and natural scene datasets. Extensive experiments verify it achieves (SOTA) performance on several benchmarks. The code and dataset are available at: \url{https://github.com/fengmulin/SMNet}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02794v1-abstract-full').style.display = 'none'; document.getElementById('2411.02794v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01618">arXiv:2411.01618</a> <span> [<a href="https://arxiv.org/pdf/2411.01618">pdf</a>, <a href="https://arxiv.org/format/2411.01618">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"> VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiwei Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jin Gao</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+F">Fudong Ge</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+G">Guan Luo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+H">Haibin Ling</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+W">Weiming Hu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01618v1-abstract-short" style="display: inline;"> Bird's-eye-view (BEV) map layout estimation requires an accurate and full understanding of the semantics for the environmental elements around the ego car to make the results coherent and realistic. Due to the challenges posed by occlusion, unfavourable imaging conditions and low resolution, \emph{generating} the BEV semantic maps corresponding to corrupted or invalid areas in the perspective view… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01618v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01618v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01618v1-abstract-full" style="display: none;"> Bird's-eye-view (BEV) map layout estimation requires an accurate and full understanding of the semantics for the environmental elements around the ego car to make the results coherent and realistic. Due to the challenges posed by occlusion, unfavourable imaging conditions and low resolution, \emph{generating} the BEV semantic maps corresponding to corrupted or invalid areas in the perspective view (PV) is appealing very recently. \emph{The question is how to align the PV features with the generative models to facilitate the map estimation}. In this paper, we propose to utilize a generative model similar to the Vector Quantized-Variational AutoEncoder (VQ-VAE) to acquire prior knowledge for the high-level BEV semantics in the tokenized discrete space. Thanks to the obtained BEV tokens accompanied with a codebook embedding encapsulating the semantics for different BEV elements in the groundtruth maps, we are able to directly align the sparse backbone image features with the obtained BEV tokens from the discrete representation learning based on a specialized token decoder module, and finally generate high-quality BEV maps with the BEV codebook embedding serving as a bridge between PV and BEV. We evaluate the BEV map layout estimation performance of our model, termed VQ-Map, on both the nuScenes and Argoverse benchmarks, achieving 62.2/47.6 mean IoU for surround-view/monocular evaluation on nuScenes, as well as 73.4 IoU for monocular evaluation on Argoverse, which all set a new record for this map layout estimation task. The code and models are available on \url{https://github.com/Z1zyw/VQ-Map}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01618v1-abstract-full').style.display = 'none'; document.getElementById('2411.01618v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01537">arXiv:2411.01537</a> <span> [<a href="https://arxiv.org/pdf/2411.01537">pdf</a>, <a href="https://arxiv.org/format/2411.01537">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </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/10.1145/3539618.3591717">10.1145/3539618.3591717 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+L">Langming Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xiangyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jingtong Gao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wanyu Wang</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+W">Wenqi Fan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yiqi Wang</a>, <a href="/search/cs?searchtype=author&query=He%2C+M">Ming He</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zitao Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qing Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01537v1-abstract-short" style="display: inline;"> Transformer models have achieved remarkable success in sequential recommender systems (SRSs). However, computing the attention matrix in traditional dot-product attention mechanisms results in a quadratic complexity with sequence lengths, leading to high computational costs for long-term sequential recommendation. Motivated by the above observation, we propose a novel L2-Normalized Linear Attentio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01537v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01537v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01537v1-abstract-full" style="display: none;"> Transformer models have achieved remarkable success in sequential recommender systems (SRSs). However, computing the attention matrix in traditional dot-product attention mechanisms results in a quadratic complexity with sequence lengths, leading to high computational costs for long-term sequential recommendation. Motivated by the above observation, we propose a novel L2-Normalized Linear Attention for the Transformer-based Sequential Recommender Systems (LinRec), which theoretically improves efficiency while preserving the learning capabilities of the traditional dot-product attention. Specifically, by thoroughly examining the equivalence conditions of efficient attention mechanisms, we show that LinRec possesses linear complexity while preserving the property of attention mechanisms. In addition, we reveal its latent efficiency properties by interpreting the proposed LinRec mechanism through a statistical lens. Extensive experiments are conducted based on two public benchmark datasets, demonstrating that the combination of LinRec and Transformer models achieves comparable or even superior performance than state-of-the-art Transformer-based SRS models while significantly improving time and memory efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01537v1-abstract-full').style.display = 'none'; document.getElementById('2411.01537v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">SIGIR 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/2411.00820">arXiv:2411.00820</a> <span> [<a href="https://arxiv.org/pdf/2411.00820">pdf</a>, <a href="https://arxiv.org/format/2411.00820">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> AutoGLM: Autonomous Foundation Agents for GUIs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiao Liu</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+B">Bo Qin</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+D">Dongzhu Liang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+G">Guang Dong</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+H">Hanyu Lai</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hanchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hanlin Zhao</a>, <a href="/search/cs?searchtype=author&query=Iong%2C+I+L">Iat Long Iong</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jiadai Sun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiaqi Wang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junjie Gao</a>, <a href="/search/cs?searchtype=author&query=Shan%2C+J">Junjun Shan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kangning Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shudan Zhang</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+S">Shuntian Yao</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+S">Siyi Cheng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+W">Wentao Yao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wenyi Zhao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinghan Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinyi Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinying Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xinyue Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yang Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yifan Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yu Yang</a> , et al. (5 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00820v1-abstract-short" style="display: inline;"> We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation unde… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00820v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00820v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00820v1-abstract-full" style="display: none;"> We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representative GUI scenarios, we have developed AutoGLM as a practical foundation agent system for real-world GUI interactions. Our approach integrates a comprehensive suite of techniques and infrastructures to create deployable agent systems suitable for user delivery. Through this development, we have derived two key insights: First, the design of an appropriate "intermediate interface" for GUI control is crucial, enabling the separation of planning and grounding behaviors, which require distinct optimization for flexibility and accuracy respectively. Second, we have developed a novel progressive training framework that enables self-evolving online curriculum reinforcement learning for AutoGLM. Our evaluations demonstrate AutoGLM's effectiveness across multiple domains. For web browsing, AutoGLM achieves a 55.2% success rate on VAB-WebArena-Lite (improving to 59.1% with a second attempt) and 96.2% on OpenTable evaluation tasks. In Android device control, AutoGLM attains a 36.2% success rate on AndroidLab (VAB-Mobile) and 89.7% on common tasks in popular Chinese APPs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00820v1-abstract-full').style.display = 'none'; document.getElementById('2411.00820v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00066">arXiv:2411.00066</a> <span> [<a href="https://arxiv.org/pdf/2411.00066">pdf</a>, <a href="https://arxiv.org/format/2411.00066">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Interpretable Language Modeling via Induction-head Ngram Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+E">Eunji Kim</a>, <a href="/search/cs?searchtype=author&query=Mantena%2C+S">Sriya Mantena</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+W">Weiwei Yang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+C">Chandan Singh</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Sungroh Yoon</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00066v1-abstract-short" style="display: inline;"> Recent large language models (LLMs) have excelled across a wide range of tasks, but their use in high-stakes and compute-limited settings has intensified the demand for interpretability and efficiency. We address this need by proposing Induction-head ngram models (Induction-Gram), a method that builds an efficient, interpretable LM by bolstering modern ngram models with a hand-engineered "inductio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00066v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00066v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00066v1-abstract-full" style="display: none;"> Recent large language models (LLMs) have excelled across a wide range of tasks, but their use in high-stakes and compute-limited settings has intensified the demand for interpretability and efficiency. We address this need by proposing Induction-head ngram models (Induction-Gram), a method that builds an efficient, interpretable LM by bolstering modern ngram models with a hand-engineered "induction head". This induction head uses a custom neural similarity metric to efficiently search the model's input context for potential next-word completions. This process enables Induction-Gram to provide ngram-level grounding for each generated token. Moreover, experiments show that this simple method significantly improves next-word prediction over baseline interpretable models (up to 26%p) and can be used to speed up LLM inference for large models through speculative decoding. We further study Induction-Gram in a natural-language neuroscience setting, where the goal is to predict the next fMRI response in a sequence. It again provides a significant improvement over interpretable models (20% relative increase in the correlation of predicted fMRI responses), potentially enabling deeper scientific investigation of language selectivity in the brain. The code is available at https://github.com/ejkim47/induction-gram. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00066v1-abstract-full').style.display = 'none'; document.getElementById('2411.00066v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.24203">arXiv:2410.24203</a> <span> [<a href="https://arxiv.org/pdf/2410.24203">pdf</a>, <a href="https://arxiv.org/format/2410.24203">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+W">Weicai Ye</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+C">Chenhao Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zheng Chen</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyao Gao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xiaoshui Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Song-Hai Zhang</a>, <a href="/search/cs?searchtype=author&query=Ouyang%2C+W">Wanli Ouyang</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tong He</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Cairong Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.24203v1-abstract-short" style="display: inline;"> Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoram… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24203v1-abstract-full').style.display = 'inline'; document.getElementById('2410.24203v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.24203v1-abstract-full" style="display: none;"> Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24203v1-abstract-full').style.display = 'none'; document.getElementById('2410.24203v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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">NeurIPS2024, Project: https://github.com/zju3dv/DiffPano; Code: https://github.com/zju3dv/DiffPano</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23771">arXiv:2410.23771</a> <span> [<a href="https://arxiv.org/pdf/2410.23771">pdf</a>, <a href="https://arxiv.org/format/2410.23771">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"> What is Wrong with Perplexity for Long-context Language Modeling? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+L">Lizhe Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifei Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhaoyang Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Jegelka%2C+S">Stefanie Jegelka</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jinyang Gao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+B">Bolin Ding</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yisen Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23771v1-abstract-short" style="display: inline;"> Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23771v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23771v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23771v1-abstract-full" style="display: none;"> Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averaging across all tokens and thereby obscuring the true performance of models in long-context scenarios. To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them. Our experiments demonstrate that LongPPL strongly correlates with performance on various long-context benchmarks (e.g., Pearson correlation of -0.96), significantly outperforming traditional PPL in predictive accuracy. Additionally, we introduce \textbf{LongCE} (Long-context Cross-Entropy) loss, a re-weighting strategy for fine-tuning that prioritizes key tokens, leading to consistent improvements across diverse benchmarks. In summary, these contributions offer deeper insights into the limitations of PPL and present effective solutions for accurately evaluating and enhancing the long-context capabilities of LLMs. Code is available at https://github.com/PKU-ML/LongPPL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23771v1-abstract-full').style.display = 'none'; document.getElementById('2410.23771v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22901">arXiv:2410.22901</a> <span> [<a href="https://arxiv.org/pdf/2410.22901">pdf</a>, <a href="https://arxiv.org/format/2410.22901">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"> HelloMeme: Integrating Spatial Knitting Attentions to Embed High-Level and Fidelity-Rich Conditions in Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shengkai Zhang</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+N">Nianhong Jiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tian Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chaojie Yang</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+C">Chenhui Xue</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+B">Boya Niu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jun Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.22901v1-abstract-short" style="display: inline;"> We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model. The core idea of this method is to optimize the attention mechanism related to 2D feature maps, which enhances the performance of the adapter. This approach was validated on the task of mem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22901v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22901v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22901v1-abstract-full" style="display: none;"> We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model. The core idea of this method is to optimize the attention mechanism related to 2D feature maps, which enhances the performance of the adapter. This approach was validated on the task of meme video generation and achieved significant results. We hope this work can provide insights for post-training tasks of large text-to-image models. Additionally, as this method demonstrates good compatibility with SD1.5 derivative models, it holds certain value for the open-source community. Therefore, we will release the related code (\url{https://songkey.github.io/hellomeme}). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22901v1-abstract-full').style.display = 'none'; document.getElementById('2410.22901v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">11 pages, 7 figures, 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07 (Primary) 68T10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.5; I.5.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22229">arXiv:2410.22229</a> <span> [<a href="https://arxiv.org/pdf/2410.22229">pdf</a>, <a href="https://arxiv.org/format/2410.22229">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Cora: Accelerating Stateful Network Applications with SmartNICs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xi%2C+S">Shaoke Xi</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiaqi Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mengqi Liu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jiamin Cao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Fuliang Li</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+K">Kai Bu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+K">Kui Ren</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+M">Minlan Yu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+D">Dennis Cai</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+E">Ennan Zhai</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="2410.22229v1-abstract-short" style="display: inline;"> With the growing performance requirements on networked applications, there is a new trend of offloading stateful network applications to SmartNICs to improve performance and reduce the total cost of ownership. However, offloading stateful network applications is non-trivial due to state operation complexity, state resource consumption, and the complicated relationship between traffic and state. Na… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22229v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22229v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22229v1-abstract-full" style="display: none;"> With the growing performance requirements on networked applications, there is a new trend of offloading stateful network applications to SmartNICs to improve performance and reduce the total cost of ownership. However, offloading stateful network applications is non-trivial due to state operation complexity, state resource consumption, and the complicated relationship between traffic and state. Naively partitioning the program by state or traffic can result in a suboptimal partition plan with higher CPU usage or even packet drops. In this paper, we propose Cora, a compiler and runtime that offloads stateful network applications to SmartNIC-accelerated hosts. Cora compiler introduces an accurate performance model for each SmartNIC and employs an efficient compiling algorithm to search the offloading plan. Cora runtime can monitor traffic dynamics and adapt to minimize CPU usage. Cora is built atop Netronome Agilio and BlueField 2 SmartNICs. Our evaluation shows that for the same throughput target, Cora can propose partition plans saving up to 94.0% CPU cores, 1.9 times more than baseline solutions. Under the same resource constraint, Cora can accelerate network functions by 44.9%-82.3%. Cora runtime can adapt to traffic changes and keep CPU usage low. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22229v1-abstract-full').style.display = 'none'; document.getElementById('2410.22229v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18469">arXiv:2410.18469</a> <span> [<a href="https://arxiv.org/pdf/2410.18469">pdf</a>, <a href="https://arxiv.org/format/2410.18469">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"> Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+C">Chung-En Sun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaodong Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+W">Weiwei Yang</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+T">Tsui-Wei Weng</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+H">Hao Cheng</a>, <a href="/search/cs?searchtype=author&query=San%2C+A">Aidan San</a>, <a href="/search/cs?searchtype=author&query=Galley%2C+M">Michel Galley</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18469v2-abstract-short" style="display: inline;"> Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current methods for generating these suffixes are computationally expensive and have low Attack Success Rates (ASR), especially against well-aligned models li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18469v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18469v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18469v2-abstract-full" style="display: none;"> Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current methods for generating these suffixes are computationally expensive and have low Attack Success Rates (ASR), especially against well-aligned models like Llama2 and Llama3. To overcome these limitations, we introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100\% ASR on various open-source LLMs. Moreover, it exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3. Beyond improving jailbreak ability, ADV-LLM provides valuable insights for future safety alignment research through its ability to generate large datasets for studying LLM safety. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18469v2-abstract-full').style.display = 'none'; document.getElementById('2410.18469v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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">18 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/2410.18406">arXiv:2410.18406</a> <span> [<a href="https://arxiv.org/pdf/2410.18406">pdf</a>, <a href="https://arxiv.org/format/2410.18406">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="Databases">cs.DB</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"> MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zhisheng Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yifu Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Zhiling Luo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jinyang Gao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yu Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18406v1-abstract-short" style="display: inline;"> The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18406v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18406v1-abstract-full" style="display: none;"> The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntactic differences among dialects and imbalanced data distribution across multiple dialects. To tackle these challenges, we propose MoMQ, a novel Mixture-of-Experts-based multi-dialect query generation framework across both relational and non-relational databases. MoMQ employs a dialect expert group for each dialect and a multi-level routing strategy to handle dialect-specific knowledge, reducing interference during query generation. Additionally, a shared expert group is introduced to address data imbalance, facilitating the transfer of common knowledge from high-resource dialects to low-resource ones. Furthermore, we have developed a high-quality multi-dialect query generation benchmark that covers relational and non-relational databases such as MySQL, PostgreSQL, Cypher for Neo4j, and nGQL for NebulaGraph. Extensive experiments have shown that MoMQ performs effectively and robustly even in resource-imbalanced scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18406v1-abstract-full').style.display = 'none'; document.getElementById('2410.18406v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18141">arXiv:2410.18141</a> <span> [<a href="https://arxiv.org/pdf/2410.18141">pdf</a>, <a href="https://arxiv.org/format/2410.18141">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jingsheng Gao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Linxu Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Weiyuan Li</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yuzhuo Fu</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+B">Bin Dai</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="2410.18141v1-abstract-short" style="display: inline;"> RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules should be jointly optimized to achieve optimal performance. To demonstrate this, we design a specific pipeline called \textbf{SmartRAG} that includes a policy network and a retriever. The policy network can serve as 1) a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18141v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18141v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18141v1-abstract-full" style="display: none;"> RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules should be jointly optimized to achieve optimal performance. To demonstrate this, we design a specific pipeline called \textbf{SmartRAG} that includes a policy network and a retriever. The policy network can serve as 1) a decision maker that decides when to retrieve, 2) a query rewriter to generate a query most suited to the retriever, and 3) an answer generator that produces the final response with/without the observations. We then propose to jointly optimize the whole system using a reinforcement learning algorithm, with the reward designed to encourage the system to achieve the best performance with minimal retrieval cost. When jointly optimized, all the modules can be aware of how other modules are working and thus find the best way to work together as a complete system. Empirical results demonstrate that the jointly optimized SmartRAG can achieve better performance than separately optimized counterparts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18141v1-abstract-full').style.display = 'none'; document.getElementById('2410.18141v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17498">arXiv:2410.17498</a> <span> [<a href="https://arxiv.org/pdf/2410.17498">pdf</a>, <a href="https://arxiv.org/format/2410.17498">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Symbolic Computation">cs.SC</span> </div> </div> <p class="title is-5 mathjax"> Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Smolensky%2C+P">Paul Smolensky</a>, <a href="/search/cs?searchtype=author&query=Fernandez%2C+R">Roland Fernandez</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z+H">Zhenghao Herbert Zhou</a>, <a href="/search/cs?searchtype=author&query=Opper%2C+M">Mattia Opper</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17498v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated impressive abilities in symbol processing through in-context learning (ICL). This success flies in the face of decades of predictions that artificial neural networks cannot master abstract symbol manipulation. We seek to understand the mechanisms that can enable robust symbol processing in transformer networks, illuminating both the unanticipated succ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17498v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17498v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17498v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated impressive abilities in symbol processing through in-context learning (ICL). This success flies in the face of decades of predictions that artificial neural networks cannot master abstract symbol manipulation. We seek to understand the mechanisms that can enable robust symbol processing in transformer networks, illuminating both the unanticipated success, and the significant limitations, of transformers in symbol processing. Borrowing insights from symbolic AI on the power of Production System architectures, we develop a high-level language, PSL, that allows us to write symbolic programs to do complex, abstract symbol processing, and create compilers that precisely implement PSL programs in transformer networks which are, by construction, 100% mechanistically interpretable. We demonstrate that PSL is Turing Universal, so the work can inform the understanding of transformer ICL in general. The type of transformer architecture that we compile from PSL programs suggests a number of paths for enhancing transformers' capabilities at symbol processing. (Note: The first section of the paper gives an extended synopsis of the entire paper.) <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17498v1-abstract-full').style.display = 'none'; document.getElementById('2410.17498v1-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 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">101 pages (including 30 pages of Appendices), 18 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.1; I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17233">arXiv:2410.17233</a> <span> [<a href="https://arxiv.org/pdf/2410.17233">pdf</a>, <a href="https://arxiv.org/format/2410.17233">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Few-shot In-Context Preference Learning Using Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+C">Chao Yu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Hong Lu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiaxuan Gao</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Q">Qixin Tan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xinting Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi Wu</a>, <a href="/search/cs?searchtype=author&query=Vinitsky%2C+E">Eugene Vinitsky</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="2410.17233v1-abstract-short" style="display: inline;"> Designing reward functions is a core component of reinforcement learning but can be challenging for truly complex behavior. Reinforcement Learning from Human Feedback (RLHF) has been used to alleviate this challenge by replacing a hand-coded reward function with a reward function learned from preferences. However, it can be exceedingly inefficient to learn these rewards as they are often learned t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17233v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17233v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17233v1-abstract-full" style="display: none;"> Designing reward functions is a core component of reinforcement learning but can be challenging for truly complex behavior. Reinforcement Learning from Human Feedback (RLHF) has been used to alleviate this challenge by replacing a hand-coded reward function with a reward function learned from preferences. However, it can be exceedingly inefficient to learn these rewards as they are often learned tabula rasa. We investigate whether Large Language Models (LLMs) can reduce this query inefficiency by converting an iterative series of human preferences into code representing the rewards. We propose In-Context Preference Learning (ICPL), a method that uses the grounding of an LLM to accelerate learning reward functions from preferences. ICPL takes the environment context and task description, synthesizes a set of reward functions, and then repeatedly updates the reward functions using human rankings of videos of the resultant policies. Using synthetic preferences, we demonstrate that ICPL is orders of magnitude more efficient than RLHF and is even competitive with methods that use ground-truth reward functions instead of preferences. Finally, we perform a series of human preference-learning trials and observe that ICPL extends beyond synthetic settings and can work effectively with humans-in-the-loop. Additional information and videos are provided at https://sites.google.com/view/few-shot-icpl/home. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17233v1-abstract-full').style.display = 'none'; document.getElementById('2410.17233v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16736">arXiv:2410.16736</a> <span> [<a href="https://arxiv.org/pdf/2410.16736">pdf</a>, <a href="https://arxiv.org/format/2410.16736">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"> Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qintong Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiahui Gao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sheng Wang</a>, <a href="/search/cs?searchtype=author&query=Pi%2C+R">Renjie Pi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xueliang Zhao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chuan Wu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xin Jiang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenguo Li</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+L">Lingpeng Kong</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="2410.16736v1-abstract-short" style="display: inline;"> Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated data or predefined task templates to direct powerful LLMs in synthesizing task-relevant data for effective model training. However, this dependence on manually… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16736v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16736v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16736v1-abstract-full" style="display: none;"> Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated data or predefined task templates to direct powerful LLMs in synthesizing task-relevant data for effective model training. However, this dependence on manually designed components may constrain the scope of generated data, potentially overlooking critical edge cases or novel scenarios that could challenge the model. In this paper, we present a novel approach, ReverseGen, designed to automatically generate effective training samples that expose the weaknesses of LLMs. Specifically, we introduce a dedicated proposer trained to produce queries that lead target models to generate unsatisfactory responses. These failure-inducing queries are then used to construct training data, helping to address the models' shortcomings and improve overall performance. Our approach is flexible and can be applied to models of various scales (3B, 7B, and 8B). We evaluate ReverseGen on three key applications (safety, honesty, and math), demonstrating that our generated data is both highly effective and diverse. Models fine-tuned with ReverseGen-generated data consistently outperform those trained on human-annotated or general model-generated data, offering a new perspective on data synthesis for task-specific LLM enhancement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16736v1-abstract-full').style.display = 'none'; document.getElementById('2410.16736v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15657">arXiv:2410.15657</a> <span> [<a href="https://arxiv.org/pdf/2410.15657">pdf</a>, <a href="https://arxiv.org/format/2410.15657">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianjun Gao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+C">Chen Cai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruoyu Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wenyang Liu</a>, <a href="/search/cs?searchtype=author&query=Yap%2C+K">Kim-Hui Yap</a>, <a href="/search/cs?searchtype=author&query=Garg%2C+K">Kratika Garg</a>, <a href="/search/cs?searchtype=author&query=Han%2C+B">Boon-Siew Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15657v1-abstract-short" style="display: inline;"> Human-object interaction (HOI) detection has seen advancements with Vision Language Models (VLMs), but these methods often depend on extensive manual annotations. Vision Large Language Models (VLLMs) can inherently recognize and reason about interactions at the image level but are computationally heavy and not designed for instance-level HOI detection. To overcome these limitations, we propose a C… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15657v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15657v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15657v1-abstract-full" style="display: none;"> Human-object interaction (HOI) detection has seen advancements with Vision Language Models (VLMs), but these methods often depend on extensive manual annotations. Vision Large Language Models (VLLMs) can inherently recognize and reason about interactions at the image level but are computationally heavy and not designed for instance-level HOI detection. To overcome these limitations, we propose a Cross-Level HOI distillation (CL-HOI) framework, which distills instance-level HOIs from VLLMs image-level understanding without the need for manual annotations. Our approach involves two stages: context distillation, where a Visual Linguistic Translator (VLT) converts visual information into linguistic form, and interaction distillation, where an Interaction Cognition Network (ICN) reasons about spatial, visual, and context relations. We design contrastive distillation losses to transfer image-level context and interaction knowledge from the teacher to the student model, enabling instance-level HOI detection. Evaluations on HICO-DET and V-COCO datasets demonstrate that our CL-HOI surpasses existing weakly supervised methods and VLLM supervised methods, showing its efficacy in detecting HOIs without manual labels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15657v1-abstract-full').style.display = 'none'; document.getElementById('2410.15657v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15600">arXiv:2410.15600</a> <span> [<a href="https://arxiv.org/pdf/2410.15600">pdf</a>, <a href="https://arxiv.org/format/2410.15600">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Patrol Security Game: Defending Against Adversary with Freedom in Attack Timing, Location, and Duration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+H">Hao-Tsung Yang</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+T">Ting-Kai Weng</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+T">Ting-Yu Chang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K+S">Kin Sum Liu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+S">Shan Lin</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jie Gao</a>, <a href="/search/cs?searchtype=author&query=Tsai%2C+S">Shih-Yu Tsai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15600v1-abstract-short" style="display: inline;"> We explored the Patrol Security Game (PSG), a robotic patrolling problem modeled as an extensive-form Stackelberg game, where the attacker determines the timing, location, and duration of their attack. Our objective is to devise a patrolling schedule with an infinite time horizon that minimizes the attacker's payoff. We demonstrated that PSG can be transformed into a combinatorial minimax problem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15600v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15600v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15600v1-abstract-full" style="display: none;"> We explored the Patrol Security Game (PSG), a robotic patrolling problem modeled as an extensive-form Stackelberg game, where the attacker determines the timing, location, and duration of their attack. Our objective is to devise a patrolling schedule with an infinite time horizon that minimizes the attacker's payoff. We demonstrated that PSG can be transformed into a combinatorial minimax problem with a closed-form objective function. By constraining the defender's strategy to a time-homogeneous first-order Markov chain (i.e., the patroller's next move depends solely on their current location), we proved that the optimal solution in cases of zero penalty involves either minimizing the expected hitting time or return time, depending on the attacker model, and that these solutions can be computed efficiently. Additionally, we observed that increasing the randomness in the patrol schedule reduces the attacker's expected payoff in high-penalty cases. However, the minimax problem becomes non-convex in other scenarios. To address this, we formulated a bi-criteria optimization problem incorporating two objectives: expected maximum reward and entropy. We proposed three graph-based algorithms and one deep reinforcement learning model, designed to efficiently balance the trade-off between these two objectives. Notably, the third algorithm can identify the optimal deterministic patrol schedule, though its runtime grows exponentially with the number of patrol spots. Experimental results validate the effectiveness and scalability of our solutions, demonstrating that our approaches outperform state-of-the-art baselines on both synthetic and real-world crime datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15600v1-abstract-full').style.display = 'none'; document.getElementById('2410.15600v1-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 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">Under review of TCPS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15115">arXiv:2410.15115</a> <span> [<a href="https://arxiv.org/pdf/2410.15115">pdf</a>, <a href="https://arxiv.org/format/2410.15115">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> On Designing Effective RL Reward at Training Time for LLM Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiaxuan Gao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Shusheng Xu</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+W">Wenjie Ye</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weilin Liu</a>, <a href="/search/cs?searchtype=author&query=He%2C+C">Chuyi He</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+W">Wei Fu</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+Z">Zhiyu Mei</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guangju Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15115v2-abstract-short" style="display: inline;"> Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However, the potential of reward models during RL training time still remains largely under-explored. It is currently unclear whether these reward models can provide addi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15115v2-abstract-full').style.display = 'inline'; document.getElementById('2410.15115v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15115v2-abstract-full" style="display: none;"> Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However, the potential of reward models during RL training time still remains largely under-explored. It is currently unclear whether these reward models can provide additional training signals to enhance the reasoning capabilities of LLMs in RL training that uses sparse success rewards, which verify the correctness of solutions. In this work, we evaluate popular reward models for RL training, including the Outcome-supervised Reward Model (ORM) and the Process-supervised Reward Model (PRM), and train a collection of LLMs for math problems using RL by combining these learned rewards with success rewards. Surprisingly, even though these learned reward models have strong inference-time performances, they may NOT help or even hurt RL training, producing worse performances than LLMs trained with the success reward only. Our analysis reveals that an LLM can receive high rewards from some of these reward models by repeating correct but unnecessary reasoning steps, leading to a severe reward hacking issue. Therefore, we introduce two novel reward refinement techniques, including Clipping and Delta. The key idea is to ensure the accumulative reward of any reasoning trajectory is upper-bounded to keep a learned reward model effective without being exploited. We evaluate our techniques with multiple reward models over a set of 1.5B and 7B LLMs on MATH and GSM8K benchmarks and demonstrate that with a carefully designed reward function, RL training without any additional supervised tuning can improve all the evaluated LLMs, including the state-of-the-art 7B LLM Qwen2.5-Math-7B-Instruct on MATH and GSM8K benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15115v2-abstract-full').style.display = 'none'; document.getElementById('2410.15115v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14157">arXiv:2410.14157</a> <span> [<a href="https://arxiv.org/pdf/2410.14157">pdf</a>, <a href="https://arxiv.org/format/2410.14157">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"> Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jiacheng Ye</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiahui Gao</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+S">Shansan Gong</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+L">Lin Zheng</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xin Jiang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenguo Li</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+L">Lingpeng Kong</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="2410.14157v1-abstract-short" style="display: inline;"> Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a novel solution to these challenges. Through the lens of subgoal imbalance, we demonstrate how diffusion models effectively learn difficult subgoals that elude autoregressive approaches. We propose Multi-granularity Diffusio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14157v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14157v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14157v1-abstract-full" style="display: none;"> Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a novel solution to these challenges. Through the lens of subgoal imbalance, we demonstrate how diffusion models effectively learn difficult subgoals that elude autoregressive approaches. We propose Multi-granularity Diffusion Modeling (MDM), which prioritizes subgoals based on difficulty during learning. On complex tasks like Countdown, Sudoku, and Boolean Satisfiability Problems, MDM significantly outperforms autoregressive models without using search techniques. For instance, MDM achieves 91.5\% and 100\% accuracy on Countdown and Sudoku, respectively, compared to 45.8\% and 20.7\% for autoregressive models. Our work highlights the potential of diffusion-based approaches in advancing AI capabilities for sophisticated language understanding and problem-solving tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14157v1-abstract-full').style.display = 'none'; document.getElementById('2410.14157v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14138">arXiv:2410.14138</a> <span> [<a href="https://arxiv.org/pdf/2410.14138">pdf</a>, <a href="https://arxiv.org/format/2410.14138">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"> ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingqi Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sheng Wang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Jingwei Dong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lei Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiahui Gao</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+L">Lingpeng Kong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chuan Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.14138v1-abstract-short" style="display: inline;"> Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation. To tackle this issue, we first identify the drawbacks of existing solutions (i.e., insufficient and irrelevant visual descriptions, and limited multi-modal capac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14138v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14138v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14138v1-abstract-full" style="display: none;"> Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation. To tackle this issue, we first identify the drawbacks of existing solutions (i.e., insufficient and irrelevant visual descriptions, and limited multi-modal capacities). We then decompose visual reasoning process into two stages: visual perception (i.e., eyesight) and textual reasoning (i.e., wisdom), and introduce a novel visual reasoning framework named ProReason. This framework features multi-run proactive perception and decoupled vision-reasoning capabilities. Briefly, given a multi-modal question, ProReason iterates proactive information collection and reasoning until the answer can be concluded with necessary and sufficient visual descriptions. Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs. Our extensive experiments demonstrate that ProReason outperforms both existing multi-step reasoning frameworks and passive peer methods on a wide range of benchmarks for both open-source and closed-source models. In addition, with the assistance of LLMs, ProReason achieves a performance improvement of up to 15% on MMMU benchmark. Our insights into existing solutions and the decoupled perspective for feasible integration of LLMs illuminate future research on visual reasoning techniques, especially LLM-assisted ones. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14138v1-abstract-full').style.display = 'none'; document.getElementById('2410.14138v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11758">arXiv:2410.11758</a> <span> [<a href="https://arxiv.org/pdf/2410.11758">pdf</a>, <a href="https://arxiv.org/format/2410.11758">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <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"> Latent Action Pretraining from Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+S">Seonghyeon Ye</a>, <a href="/search/cs?searchtype=author&query=Jang%2C+J">Joel Jang</a>, <a href="/search/cs?searchtype=author&query=Jeon%2C+B">Byeongguk Jeon</a>, <a href="/search/cs?searchtype=author&query=Joo%2C+S">Sejune Joo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jianwei Yang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+B">Baolin Peng</a>, <a href="/search/cs?searchtype=author&query=Mandlekar%2C+A">Ajay Mandlekar</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+R">Reuben Tan</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+Y">Yu-Wei Chao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+B+Y">Bill Yuchen Lin</a>, <a href="/search/cs?searchtype=author&query=Liden%2C+L">Lars Liden</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+K">Kimin Lee</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a>, <a href="/search/cs?searchtype=author&query=Zettlemoyer%2C+L">Luke Zettlemoyer</a>, <a href="/search/cs?searchtype=author&query=Fox%2C+D">Dieter Fox</a>, <a href="/search/cs?searchtype=author&query=Seo%2C+M">Minjoon Seo</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="2410.11758v1-abstract-short" style="display: inline;"> We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11758v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11758v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11758v1-abstract-full" style="display: none;"> We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a method to learn from internet-scale videos that do not have robot action labels. We first train an action quantization model leveraging VQ-VAE-based objective to learn discrete latent actions between image frames, then pretrain a latent VLA model to predict these latent actions from observations and task descriptions, and finally finetune the VLA on small-scale robot manipulation data to map from latent to robot actions. Experimental results demonstrate that our method significantly outperforms existing techniques that train robot manipulation policies from large-scale videos. Furthermore, it outperforms the state-of-the-art VLA model trained with robotic action labels on real-world manipulation tasks that require language conditioning, generalization to unseen objects, and semantic generalization to unseen instructions. Training only on human manipulation videos also shows positive transfer, opening up the potential for leveraging web-scale data for robotics foundation model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11758v1-abstract-full').style.display = 'none'; document.getElementById('2410.11758v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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">Website: https://latentactionpretraining.github.io</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.10818">arXiv:2410.10818</a> <span> [<a href="https://arxiv.org/pdf/2410.10818">pdf</a>, <a href="https://arxiv.org/format/2410.10818">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cai%2C+M">Mu Cai</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+R">Reuben Tan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianrui Zhang</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+B">Bocheng Zou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+F">Feng Yao</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+F">Fangrui Zhu</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jing Gu</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+Y">Yiwu Zhong</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+Y">Yuzhang Shang</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Y">Yao Dou</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jaden Park</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianfeng Gao</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+Y+J">Yong Jae Lee</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jianwei Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.10818v2-abstract-short" style="display: inline;"> Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are incompetent at evaluating models for temporal understanding. In this paper, we introduce TemporalBench, a new benchmark dedicated to evaluating fine-grained temporal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10818v2-abstract-full').style.display = 'inline'; document.getElementById('2410.10818v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10818v2-abstract-full" style="display: none;"> Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are incompetent at evaluating models for temporal understanding. In this paper, we introduce TemporalBench, a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. TemporalBench consists of ~10K video question-answer pairs, derived from ~2K high-quality human annotations detailing the temporal dynamics in video clips. As a result, our benchmark provides a unique testbed for evaluating various temporal understanding and reasoning abilities such as action frequency, motion magnitude, event order, etc. Moreover, it enables evaluations on various tasks like both video question answering and captioning, both short and long video understanding, as well as different models such as multimodal video embedding models and text generation models. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench, demonstrating a significant gap (~30%) between humans and AI in temporal understanding. Furthermore, we notice a critical pitfall for multi-choice QA where LLMs can detect the subtle changes in negative captions and find a centralized description as a cue for its prediction, where we propose Multiple Binary Accuracy (MBA) to correct such bias. We hope that TemporalBench can foster research on improving models' temporal reasoning capabilities. Both dataset and evaluation code will be made available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10818v2-abstract-full').style.display = 'none'; document.getElementById('2410.10818v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 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">Project Page: https://temporalbench.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.10148">arXiv:2410.10148</a> <span> [<a href="https://arxiv.org/pdf/2410.10148">pdf</a>, <a href="https://arxiv.org/format/2410.10148">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> $伪$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junkang Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xue Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhengyi Yang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiancan Wu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jinyang Gao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+B">Bolin Ding</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiang Wang</a>, <a href="/search/cs?searchtype=author&query=He%2C+X">Xiangnan He</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="2410.10148v3-abstract-short" style="display: inline;"> Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces challenges in computational efficiency and training stability. Recent methods like Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO) hav… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10148v3-abstract-full').style.display = 'inline'; document.getElementById('2410.10148v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10148v3-abstract-full" style="display: none;"> Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces challenges in computational efficiency and training stability. Recent methods like Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO) have proposed offline alternatives to RLHF, simplifying the process by reparameterizing the reward function. However, DPO depends on a potentially suboptimal reference model, and SimPO's assumption of a fixed target reward margin may lead to suboptimal decisions in diverse data settings. In this work, we propose $伪$-DPO, an adaptive preference optimization algorithm designed to address these limitations by introducing a dynamic reward margin. Specifically, $伪$-DPO employs an adaptive preference distribution, balancing the policy model and the reference model to achieve personalized reward margins. We provide theoretical guarantees for $伪$-DPO, demonstrating its effectiveness as a surrogate optimization objective and its ability to balance alignment and diversity through KL divergence control. Empirical evaluations on AlpacaEval 2 and Arena-Hard show that $伪$-DPO consistently outperforms DPO and SimPO across various model settings, establishing it as a robust approach for fine-tuning LLMs. Our method achieves significant improvements in win rates, highlighting its potential as a powerful tool for LLM alignment. The code is available at https://github.com/junkangwu/alpha-DPO <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10148v3-abstract-full').style.display = 'none'; document.getElementById('2410.10148v3-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09975">arXiv:2410.09975</a> <span> [<a href="https://arxiv.org/pdf/2410.09975">pdf</a>, <a href="https://arxiv.org/format/2410.09975">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"> Optimizing Waste Management with Advanced Object Detection for Garbage Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kuang%2C+E+Z">Everest Z. Kuang</a>, <a href="/search/cs?searchtype=author&query=Bhandari%2C+K+R">Kushal Raj Bhandari</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianxi Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.09975v2-abstract-short" style="display: inline;"> Garbage production and littering are persistent global issues that pose significant environmental challenges. Despite large-scale efforts to manage waste through collection and sorting, existing approaches remain inefficient, leading to inadequate recycling and disposal. Therefore, developing advanced AI-based systems is less labor intensive approach for addressing the growing waste problem more e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09975v2-abstract-full').style.display = 'inline'; document.getElementById('2410.09975v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09975v2-abstract-full" style="display: none;"> Garbage production and littering are persistent global issues that pose significant environmental challenges. Despite large-scale efforts to manage waste through collection and sorting, existing approaches remain inefficient, leading to inadequate recycling and disposal. Therefore, developing advanced AI-based systems is less labor intensive approach for addressing the growing waste problem more effectively. These models can be applied to sorting systems or possibly waste collection robots that may produced in the future. AI models have grown significantly at identifying objects through object detection. This paper reviews the implementation of AI models for classifying trash through object detection, specifically focusing on using YOLO V5 for training and testing. The study demonstrates how YOLO V5 can effectively identify various types of waste, including plastic, paper, glass, metal, cardboard, and biodegradables. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09975v2-abstract-full').style.display = 'none'; document.getElementById('2410.09975v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09444">arXiv:2410.09444</a> <span> [<a href="https://arxiv.org/pdf/2410.09444">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Diabetic retinopathy image classification method based on GreenBen data augmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yutong Liu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jie Gao</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Haijiang Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.09444v1-abstract-short" style="display: inline;"> For the diagnosis of diabetes retinopathy (DR) images, this paper proposes a classification method based on artificial intelligence. The core lies in a new data augmentation method, GreenBen, which first extracts the green channel grayscale image from the retinal image and then performs Ben enhancement. Considering that diabetes macular edema (DME) is a complication closely related to DR, this pap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09444v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09444v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09444v1-abstract-full" style="display: none;"> For the diagnosis of diabetes retinopathy (DR) images, this paper proposes a classification method based on artificial intelligence. The core lies in a new data augmentation method, GreenBen, which first extracts the green channel grayscale image from the retinal image and then performs Ben enhancement. Considering that diabetes macular edema (DME) is a complication closely related to DR, this paper constructs a joint classification framework of DR and DME based on multi task learning and attention module, and uses GreenBen to enhance its data to reduce the difference of DR images and improve the accuracy of model classification. We conducted extensive experiments on three publicly available datasets, and our method achieved the best results. For GreenBen, whether based on the ResNet50 network or the Swin Transformer network, whether for individual classification or joint DME classification, compared with other data augmentation methods, GreenBen achieved stable and significant improvements in DR classification results, with an accuracy increase of 10%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09444v1-abstract-full').style.display = 'none'; document.getElementById('2410.09444v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08781">arXiv:2410.08781</a> <span> [<a href="https://arxiv.org/pdf/2410.08781">pdf</a>, <a href="https://arxiv.org/format/2410.08781">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"> VideoSAM: Open-World Video Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+P">Pinxue Guo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zixu Zhao</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jianxiong Gao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chongruo Wu</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tong He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+T">Tianjun Xiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenqiang Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.08781v1-abstract-short" style="display: inline;"> Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelled in static image segmentation, extending its capabilities to video segmentation poses significant challenges. We tackle two major hurdles: a) SAM's e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08781v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08781v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08781v1-abstract-full" style="display: none;"> Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelled in static image segmentation, extending its capabilities to video segmentation poses significant challenges. We tackle two major hurdles: a) SAM's embedding limitations in associating objects across frames, and b) granularity inconsistencies in object segmentation. To this end, we introduce VideoSAM, an end-to-end framework designed to address these challenges by improving object tracking and segmentation consistency in dynamic environments. VideoSAM integrates an agglomerated backbone, RADIO, enabling object association through similarity metrics and introduces Cycle-ack-Pairs Propagation with a memory mechanism for stable object tracking. Additionally, we incorporate an autoregressive object-token mechanism within the SAM decoder to maintain consistent granularity across frames. Our method is extensively evaluated on the UVO and BURST benchmarks, and robotic videos from RoboTAP, demonstrating its effectiveness and robustness in real-world scenarios. All codes will be available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08781v1-abstract-full').style.display = 'none'; document.getElementById('2410.08781v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08611">arXiv:2410.08611</a> <span> [<a href="https://arxiv.org/pdf/2410.08611">pdf</a>, <a href="https://arxiv.org/format/2410.08611">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"> Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+M">Mengyuan Chen</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyu Gao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+C">Changsheng Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.08611v1-abstract-short" style="display: inline;"> A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-trained vision-language model to perform classification on both in-distribution (ID) and OOD labels. In this paper, we theorize that enhancing performance requires expanding the semantic pool, while increasing the expected pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08611v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08611v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08611v1-abstract-full" style="display: none;"> A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-trained vision-language model to perform classification on both in-distribution (ID) and OOD labels. In this paper, we theorize that enhancing performance requires expanding the semantic pool, while increasing the expected probability of selected OOD labels being activated by OOD samples, and ensuring low mutual dependence among the activations of these OOD labels. A natural expansion manner is to adopt a larger lexicon; however, the inevitable introduction of numerous synonyms and uncommon words fails to meet the above requirements, indicating that viable expansion manners move beyond merely selecting words from a lexicon. Since OOD detection aims to correctly classify input images into ID/OOD class groups, we can "make up" OOD label candidates which are not standard class names but beneficial for the process. Observing that the original semantic pool is comprised of unmodified specific class names, we correspondingly construct a conjugated semantic pool (CSP) consisting of modified superclass names, each serving as a cluster center for samples sharing similar properties across different categories. Consistent with our established theory, expanding OOD label candidates with the CSP satisfies the requirements and outperforms existing works by 7.89% in FPR95. Codes are available in https://github.com/MengyuanChen21/NeurIPS2024-CSP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08611v1-abstract-full').style.display = 'none'; document.getElementById('2410.08611v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">28 pages, accepted by NeurIPS 2024</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=Gao%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Gao%2C+J&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository