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 1,644 results for author: <span class="mathjax">Lin, Y</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=Lin%2C+Y">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="Lin, Y"> </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=Lin%2C+Y&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="Lin, Y"> <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=Lin%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&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/2411.13941">arXiv:2411.13941</a> <span> [<a href="https://arxiv.org/pdf/2411.13941">pdf</a>, <a href="https://arxiv.org/format/2411.13941">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"> LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yalan Lin</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yingwei Ma</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+R">Rongyu Cao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Binhua Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+F">Fei Huang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+X">Xiaodong Gu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yongbin Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13941v1-abstract-short" style="display: inline;"> Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed for this task, they primarily address common, widespread errors and struggle to adapt to unique, evolving errors specific to individual code repositories. To fil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13941v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13941v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13941v1-abstract-full" style="display: none;"> Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed for this task, they primarily address common, widespread errors and struggle to adapt to unique, evolving errors specific to individual code repositories. To fill this gap, we propose EvoCoder, a multi-agent continuous learning framework for issue code reproduction. EvoCoder adopts a reflection mechanism that allows the LLM to continuously learn from previously resolved problems and dynamically refine its strategies to new emerging challenges. To prevent experience bloating, EvoCoder introduces a novel hierarchical experience pool that enables the model to adaptively update common and repo-specific experiences. Our experimental results show a 20\% improvement in issue reproduction rates over existing SOTA methods. Furthermore, integrating our reproduction mechanism significantly boosts the overall accuracy of the existing issue-resolving pipeline. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13941v1-abstract-full').style.display = 'none'; document.getElementById('2411.13941v1-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/2411.13676">arXiv:2411.13676</a> <span> [<a href="https://arxiv.org/pdf/2411.13676">pdf</a>, <a href="https://arxiv.org/format/2411.13676">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"> Hymba: A Hybrid-head Architecture for Small Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dong%2C+X">Xin Dong</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yonggan Fu</a>, <a href="/search/cs?searchtype=author&query=Diao%2C+S">Shizhe Diao</a>, <a href="/search/cs?searchtype=author&query=Byeon%2C+W">Wonmin Byeon</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zijia Chen</a>, <a href="/search/cs?searchtype=author&query=Mahabaleshwarkar%2C+A+S">Ameya Sunil Mahabaleshwarkar</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shih-Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Van+Keirsbilck%2C+M">Matthijs Van Keirsbilck</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+M">Min-Hung Chen</a>, <a href="/search/cs?searchtype=author&query=Suhara%2C+Y">Yoshi Suhara</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yingyan Lin</a>, <a href="/search/cs?searchtype=author&query=Kautz%2C+J">Jan Kautz</a>, <a href="/search/cs?searchtype=author&query=Molchanov%2C+P">Pavlo Molchanov</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="2411.13676v1-abstract-short" style="display: inline;"> We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide high-resolution recall, while SSM heads enable efficient context summarization. Additionally, we introduce learnable meta tokens that are prepended to prompts, storing criti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13676v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13676v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13676v1-abstract-full" style="display: none;"> We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide high-resolution recall, while SSM heads enable efficient context summarization. Additionally, we introduce learnable meta tokens that are prepended to prompts, storing critical information and alleviating the "forced-to-attend" burden associated with attention mechanisms. This model is further optimized by incorporating cross-layer key-value (KV) sharing and partial sliding window attention, resulting in a compact cache size. During development, we conducted a controlled study comparing various architectures under identical settings and observed significant advantages of our proposed architecture. Notably, Hymba achieves state-of-the-art results for small LMs: Our Hymba-1.5B-Base model surpasses all sub-2B public models in performance and even outperforms Llama-3.2-3B with 1.32% higher average accuracy, an 11.67x cache size reduction, and 3.49x throughput. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13676v1-abstract-full').style.display = 'none'; document.getElementById('2411.13676v1-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">20 pages, models are available on huggingface</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12913">arXiv:2411.12913</a> <span> [<a href="https://arxiv.org/pdf/2411.12913">pdf</a>, <a href="https://arxiv.org/format/2411.12913">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"> MLDGG: Meta-Learning for Domain Generalization on Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tian%2C+Q">Qin Tian</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Chen Zhao</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+M">Minglai Shao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wenjun Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yujie Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Dong 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="2411.12913v1-abstract-short" style="display: inline;"> Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods often rely on static encoders directly applied to the target domain, constraining its flexible adaptability. In contrast to conventional methodologies, which concen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12913v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12913v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12913v1-abstract-full" style="display: none;"> Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods often rely on static encoders directly applied to the target domain, constraining its flexible adaptability. In contrast to conventional methodologies, which concentrate on developing specific generalized models, our framework, MLDGG, endeavors to achieve adaptable generalization across diverse domains by integrating cross-multi-domain meta-learning with structure learning and semantic identification. Initially, it introduces a generalized structure learner to mitigate the adverse effects of task-unrelated edges, enhancing the comprehensiveness of representations learned by Graph Neural Networks (GNNs) while capturing shared structural information across domains. Subsequently, a representation learner is designed to disentangle domain-invariant semantic and domain-specific variation information in node embedding by leveraging causal reasoning for semantic identification, further enhancing generalization. In the context of meta-learning, meta-parameters for both learners are optimized to facilitate knowledge transfer and enable effective adaptation to graphs through fine-tuning within the target domains, where target graphs are inaccessible during training. Our empirical results demonstrate that MLDGG surpasses baseline methods, showcasing its effectiveness in three different distribution shift settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12913v1-abstract-full').style.display = 'none'; document.getElementById('2411.12913v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in KDD 2025 (research track)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12690">arXiv:2411.12690</a> <span> [<a href="https://arxiv.org/pdf/2411.12690">pdf</a>, <a href="https://arxiv.org/format/2411.12690">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> MORE-Stress: Model Order Reduction based Efficient Numerical Algorithm for Thermal Stress Simulation of TSV Arrays in 2.5D/3D IC </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tianxiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qipan Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yibo Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Runsheng Wang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+R">Ru 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="2411.12690v1-abstract-short" style="display: inline;"> Thermomechanical stress induced by through-silicon vias (TSVs) plays an important role in the performance and reliability analysis of 2.5D/3D ICs. While the finite element method (FEM) adopted by commercial software can provide accurate simulation results, it is very time- and memory-consuming for large-scale analysis. Over the past decade, the linear superposition method has been utilized to perf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12690v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12690v1-abstract-full" style="display: none;"> Thermomechanical stress induced by through-silicon vias (TSVs) plays an important role in the performance and reliability analysis of 2.5D/3D ICs. While the finite element method (FEM) adopted by commercial software can provide accurate simulation results, it is very time- and memory-consuming for large-scale analysis. Over the past decade, the linear superposition method has been utilized to perform fast thermal stress estimations of TSV arrays, but it suffers from a lack of accuracy. In this paper, we propose MORE-Stress, a novel strict numerical algorithm for efficient thermal stress simulation of TSV arrays based on model order reduction. Extensive experimental results demonstrate that our algorithm can realize a 153-504 times reduction in computational time and a 39-115 times reduction in memory usage compared with the commercial software ANSYS, with negligible errors less than 1%. Our algorithm is as efficient as the linear superposition method, with an order of magnitude smaller errors and fast convergence. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12690v1-abstract-full').style.display = 'none'; document.getElementById('2411.12690v1-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> <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">2025 Design, Automation & Test in Europe Conference & Exhibition (DATE)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12584">arXiv:2411.12584</a> <span> [<a href="https://arxiv.org/pdf/2411.12584">pdf</a>, <a href="https://arxiv.org/format/2411.12584">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"> Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+X">Xudong Yan</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+S">Songhe Feng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yueguan Lin</a>, <a href="/search/cs?searchtype=author&query=Fei%2C+H">Haojun Fei</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="2411.12584v1-abstract-short" style="display: inline;"> Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attribute and object by extracting shared and exclusive parts between image pairs sharing the same attribute (object), as well as aligning them with pretrained word embeddings to improve unseen attribute-object recognition. Despite the si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12584v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12584v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12584v1-abstract-full" style="display: none;"> Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attribute and object by extracting shared and exclusive parts between image pairs sharing the same attribute (object), as well as aligning them with pretrained word embeddings to improve unseen attribute-object recognition. Despite the significant achievements of existing efforts, they are hampered by three limitations: (1) the efficacy of disentanglement is compromised due to the influence of the background and the intricate entanglement of attribute with object in the same parts. (2) existing word embeddings fail to capture complex multimodal semantic information. (3) overconfidence exhibited by existing models in seen compositions hinders their generalization to novel compositions. Being aware of these, we propose a novel framework named Multimodal Large Language Model (MLLM) embeddings and attribute smoothing guided disentanglement (TRIDENT) for CZSL. First, we leverage feature adaptive aggregation modules to mitigate the impact of background, and utilize learnable condition masks to capture multigranularity features for disentanglement. Then, the last hidden states of MLLM are employed as word embeddings for their superior representation capabilities. Moreover, we propose attribute smoothing with auxiliary attributes generated by Large Language Model (LLM) for seen compositions, addressing the issue of overconfidence by encouraging the model to learn more attributes in one given composition. Extensive experiments demonstrate that TRIDENT achieves state-of-the-art performance on three benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12584v1-abstract-full').style.display = 'none'; document.getElementById('2411.12584v1-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/2411.12126">arXiv:2411.12126</a> <span> [<a href="https://arxiv.org/pdf/2411.12126">pdf</a>, <a href="https://arxiv.org/format/2411.12126">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"> MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ouyang%2C+X">Xiaomin Ouyang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jason Wu</a>, <a href="/search/cs?searchtype=author&query=Kimura%2C+T">Tomoyoshi Kimura</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yihan Lin</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+G">Gunjan Verma</a>, <a href="/search/cs?searchtype=author&query=Abdelzaher%2C+T">Tarek Abdelzaher</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+M">Mani Srivastava</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="2411.12126v1-abstract-short" style="display: inline;"> Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of complete multimodal data. However, such a setting is impractical in real-world IoT sensing applications where data is typically collected by distributed nodes with heterogeneous data modalities, and is also rarely lab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12126v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12126v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12126v1-abstract-full" style="display: none;"> Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of complete multimodal data. However, such a setting is impractical in real-world IoT sensing applications where data is typically collected by distributed nodes with heterogeneous data modalities, and is also rarely labeled. In this paper, we propose MMBind, a new framework for multimodal learning on distributed and heterogeneous IoT data. The key idea of MMBind is to construct a pseudo-paired multimodal dataset for model training by binding data from disparate sources and incomplete modalities through a sufficiently descriptive shared modality. We demonstrate that data of different modalities observing similar events, even captured at different times and locations, can be effectively used for multimodal training. Moreover, we propose an adaptive multimodal learning architecture capable of training models with heterogeneous modality combinations, coupled with a weighted contrastive learning approach to handle domain shifts among disparate data. Evaluations on ten real-world multimodal datasets highlight that MMBind outperforms state-of-the-art baselines under varying data incompleteness and domain shift, and holds promise for advancing multimodal foundation model training in IoT applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12126v1-abstract-full').style.display = 'none'; document.getElementById('2411.12126v1-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/2411.11917">arXiv:2411.11917</a> <span> [<a href="https://arxiv.org/pdf/2411.11917">pdf</a>, <a href="https://arxiv.org/format/2411.11917">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"> FCC: Fully Connected Correlation for Few-Shot Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Moon%2C+S">Seonghyeon Moon</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+H">Haein Kong</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+M+H">Muhammad Haris Khan</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yuewei Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11917v1-abstract-short" style="display: inline;"> Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable vari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11917v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11917v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11917v1-abstract-full" style="display: none;"> Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable variation in appearance, texture, or scale across the support and query images. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer features. However, we found these approaches can offer limited and partial information when advanced models like Vision Transformers are used as the backbone. Vision Transformer encoders have a multi-layer structure with identical shapes in their intermediate layers. Leveraging the feature comparison from all layers in the encoder can enhance the performance of few-shot segmentation. We introduce FCC (Fully Connected Correlation) to integrate pixel-level correlations between support and query features, capturing associations that reveal target-specific patterns and correspondences in both same-layers and cross-layers. FCC captures previously inaccessible target information, effectively addressing the limitations of support mask. Our approach consistently demonstrates state-of-the-art performance on PASCAL, COCO, and domain shift tests. We conducted an ablation study and cross-layer correlation analysis to validate FCC's core methodology. These findings reveal the effectiveness of FCC in enhancing prior information and overall model performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11917v1-abstract-full').style.display = 'none'; document.getElementById('2411.11917v1-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/2411.11082">arXiv:2411.11082</a> <span> [<a href="https://arxiv.org/pdf/2411.11082">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+H">Haoran Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xichuan Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yingcheng Lin</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+M">Min Tian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Liyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+C">Cong Shi</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="2411.11082v1-abstract-short" style="display: inline;"> The prevailing of artificial intelligence-of-things calls for higher energy-efficient edge computing paradigms, such as neuromorphic agents leveraging brain-inspired spiking neural network (SNN) models based on spatiotemporally sparse binary activations. However, the lack of efficient and high-accuracy deep SNN learning algorithms prevents them from practical edge deployments with a strictly bound… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11082v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11082v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11082v1-abstract-full" style="display: none;"> The prevailing of artificial intelligence-of-things calls for higher energy-efficient edge computing paradigms, such as neuromorphic agents leveraging brain-inspired spiking neural network (SNN) models based on spatiotemporally sparse binary activations. However, the lack of efficient and high-accuracy deep SNN learning algorithms prevents them from practical edge deployments with a strictly bounded cost. In this paper, we propose a spatiotemporal orthogonal propagation (STOP) algorithm to tack this challenge. Our algorithm enables fully synergistic learning of synaptic weights as well as firing thresholds and leakage factors in spiking neurons to improve SNN accuracy, while under a unified temporally-forward trace-based framework to mitigate the huge memory requirement for storing neural states of all time-steps in the forward pass. Characteristically, the spatially-backward neuronal errors and temporally-forward traces propagate orthogonally to and independently of each other, substantially reducing computational overhead. Our STOP algorithm obtained high recognition accuracies of 99.53%, 94.84%, 74.92%, 98.26% and 77.10% on the MNIST, CIFAR-10, CIFAR-100, DVS-Gesture and DVS-CIFAR10 datasets with adequate SNNs of intermediate scales from LeNet-5 to ResNet-18. Compared with other deep SNN training works, our method is more plausible for edge intelligent scenarios where resources are limited but high-accuracy in-situ learning is desired. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11082v1-abstract-full').style.display = 'none'; document.getElementById('2411.11082v1-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">13 pages (exclude supplementary), 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11053">arXiv:2411.11053</a> <span> [<a href="https://arxiv.org/pdf/2411.11053">pdf</a>, <a href="https://arxiv.org/format/2411.11053">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"> SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+B">Bin Xu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiguan Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinghao Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yang 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="2411.11053v3-abstract-short" style="display: inline;"> Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decomposition capabilities. To address this issue, we propose a reasoning-augmented data generation process, SRA-MCTS, which guides the model to autonomously generate high-quality intermed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11053v3-abstract-full').style.display = 'inline'; document.getElementById('2411.11053v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11053v3-abstract-full" style="display: none;"> Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decomposition capabilities. To address this issue, we propose a reasoning-augmented data generation process, SRA-MCTS, which guides the model to autonomously generate high-quality intermediate reasoning paths. This creates a positive feedback loop, enabling continuous improvement. Our method operates entirely through the model itself without requiring additional supervision. By synthesizing natural language reasoning paths and translating them into executable code, the approach ensures analytical accuracy and enhances the success rate in solving complex tasks. Experimental results show that, even without additional supervisory signals, our method achieves performance improvements across different model scales, demonstrating the significant potential of self-improvement in small models. Furthermore, the method remains robust when traditional Chain-of-Thought (CoT) approaches exhibit performance degradation, with notable improvements observed in diversity metrics such as pass@10. We encourage further exploration of reasoning processes within training data to enhance the ability of language models to address complex problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11053v3-abstract-full').style.display = 'none'; document.getElementById('2411.11053v3-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">v1</span> submitted 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/2411.10606">arXiv:2411.10606</a> <span> [<a href="https://arxiv.org/pdf/2411.10606">pdf</a>, <a href="https://arxiv.org/format/2411.10606">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"> AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yonggan Fu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhongzhi Yu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Junwei Li</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+J">Jiayi Qian</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongan Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiangchi Yuan</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+D">Dachuan Shi</a>, <a href="/search/cs?searchtype=author&query=Yakunin%2C+R">Roman Yakunin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y+C">Yingyan Celine Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10606v1-abstract-short" style="display: inline;"> Motivated by the transformative capabilities of large language models (LLMs) across various natural language tasks, there has been a growing demand to deploy these models effectively across diverse real-world applications and platforms. However, the challenge of efficiently deploying LLMs has become increasingly pronounced due to the varying application-specific performance requirements and the ra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10606v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10606v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10606v1-abstract-full" style="display: none;"> Motivated by the transformative capabilities of large language models (LLMs) across various natural language tasks, there has been a growing demand to deploy these models effectively across diverse real-world applications and platforms. However, the challenge of efficiently deploying LLMs has become increasingly pronounced due to the varying application-specific performance requirements and the rapid evolution of computational platforms, which feature diverse resource constraints and deployment flows. These varying requirements necessitate LLMs that can adapt their structures (depth and width) for optimal efficiency across different platforms and application specifications. To address this critical gap, we propose AmoebaLLM, a novel framework designed to enable the instant derivation of LLM subnets of arbitrary shapes, which achieve the accuracy-efficiency frontier and can be extracted immediately after a one-time fine-tuning. In this way, AmoebaLLM significantly facilitates rapid deployment tailored to various platforms and applications. Specifically, AmoebaLLM integrates three innovative components: (1) a knowledge-preserving subnet selection strategy that features a dynamic-programming approach for depth shrinking and an importance-driven method for width shrinking; (2) a shape-aware mixture of LoRAs to mitigate gradient conflicts among subnets during fine-tuning; and (3) an in-place distillation scheme with loss-magnitude balancing as the fine-tuning objective. Extensive experiments validate that AmoebaLLM not only sets new standards in LLM adaptability but also successfully delivers subnets that achieve state-of-the-art trade-offs between accuracy and efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10606v1-abstract-full').style.display = 'none'; document.getElementById('2411.10606v1-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">Accepted at 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/2411.09577">arXiv:2411.09577</a> <span> [<a href="https://arxiv.org/pdf/2411.09577">pdf</a>, <a href="https://arxiv.org/format/2411.09577">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> SimTube: Generating Simulated Video Comments through Multimodal AI and User Personas </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hung%2C+Y">Yu-Kai Hung</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yun-Chien Huang</a>, <a href="/search/cs?searchtype=author&query=Su%2C+T">Ting-Yu Su</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yen-Ting Lin</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Lung-Pan Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bryan Wang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+S">Shao-Hua Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09577v2-abstract-short" style="display: inline;"> Audience feedback is crucial for refining video content, yet it typically comes after publication, limiting creators' ability to make timely adjustments. To bridge this gap, we introduce SimTube, a generative AI system designed to simulate audience feedback in the form of video comments before a video's release. SimTube features a computational pipeline that integrates multimodal data from the vid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09577v2-abstract-full').style.display = 'inline'; document.getElementById('2411.09577v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09577v2-abstract-full" style="display: none;"> Audience feedback is crucial for refining video content, yet it typically comes after publication, limiting creators' ability to make timely adjustments. To bridge this gap, we introduce SimTube, a generative AI system designed to simulate audience feedback in the form of video comments before a video's release. SimTube features a computational pipeline that integrates multimodal data from the video-such as visuals, audio, and metadata-with user personas derived from a broad and diverse corpus of audience demographics, generating varied and contextually relevant feedback. Furthermore, the system's UI allows creators to explore and customize the simulated comments. Through a comprehensive evaluation-comprising quantitative analysis, crowd-sourced assessments, and qualitative user studies-we show that SimTube's generated comments are not only relevant, believable, and diverse but often more detailed and informative than actual audience comments, highlighting its potential to help creators refine their content before release. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09577v2-abstract-full').style.display = 'none'; document.getElementById('2411.09577v2-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">v1</span> submitted 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/2411.09360">arXiv:2411.09360</a> <span> [<a href="https://arxiv.org/pdf/2411.09360">pdf</a>, <a href="https://arxiv.org/format/2411.09360">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> D4W: Dependable Data-Driven Dynamics for Wheeled Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yunfeng Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Minghuan Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yong Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09360v1-abstract-short" style="display: inline;"> Wheeled robots have gained significant attention due to their wide range of applications in manufacturing, logistics, and service industries. However, due to the difficulty of building a highly accurate dynamics model for wheeled robots, developing and testing control algorithms for them remains challenging and time-consuming, requiring extensive physical experimentation. To address this problem,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09360v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09360v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09360v1-abstract-full" style="display: none;"> Wheeled robots have gained significant attention due to their wide range of applications in manufacturing, logistics, and service industries. However, due to the difficulty of building a highly accurate dynamics model for wheeled robots, developing and testing control algorithms for them remains challenging and time-consuming, requiring extensive physical experimentation. To address this problem, we propose D4W, i.e., Dependable Data-Driven Dynamics for Wheeled Robots, a simulation framework incorporating data-driven methods to accelerate the development and evaluation of algorithms for wheeled robots. The key contribution of D4W is a solution that utilizes real-world sensor data to learn accurate models of robot dynamics. The learned dynamics can capture complex robot behaviors and interactions with the environment throughout simulations, surpassing the limitations of analytical methods, which only work in simplified scenarios. Experimental results show that D4W achieves the best simulation accuracy compared to traditional approaches, allowing for rapid iteration of wheel robot algorithms with less or no need for fine-tuning in reality. We further verify the usability and practicality of the proposed framework through integration with existing simulators and controllers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09360v1-abstract-full').style.display = 'none'; document.getElementById('2411.09360v1-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">The Fifth International Conference on Distributed Artificial Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09068">arXiv:2411.09068</a> <span> [<a href="https://arxiv.org/pdf/2411.09068">pdf</a>, <a href="https://arxiv.org/format/2411.09068">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Liner Shipping Network Design with Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dutta%2C+U">Utsav Dutta</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yifan Lin</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Z+L">Zhaoyang Larry Jin</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="2411.09068v1-abstract-short" style="display: inline;"> This paper proposes a novel reinforcement learning framework to address the Liner Shipping Network Design Problem (LSNDP), a challenging combinatorial optimization problem focused on designing cost-efficient maritime shipping routes. Traditional methods for solving the LSNDP typically involve decomposing the problem into sub-problems, such as network design and multi-commodity flow, which are then… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09068v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09068v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09068v1-abstract-full" style="display: none;"> This paper proposes a novel reinforcement learning framework to address the Liner Shipping Network Design Problem (LSNDP), a challenging combinatorial optimization problem focused on designing cost-efficient maritime shipping routes. Traditional methods for solving the LSNDP typically involve decomposing the problem into sub-problems, such as network design and multi-commodity flow, which are then tackled using approximate heuristics or large neighborhood search (LNS) techniques. In contrast, our approach employs a model-free reinforcement learning algorithm on the network design, integrated with a heuristic-based multi-commodity flow solver, to produce competitive results on the publicly available LINERLIB benchmark. Additionally, our method also demonstrates generalization capabilities by producing competitive solutions on the benchmark instances after training on perturbed instances. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09068v1-abstract-full').style.display = 'none'; document.getElementById('2411.09068v1-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/2411.08332">arXiv:2411.08332</a> <span> [<a href="https://arxiv.org/pdf/2411.08332">pdf</a>, <a href="https://arxiv.org/ps/2411.08332">ps</a>, <a href="https://arxiv.org/format/2411.08332">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Grigorescu%2C+E">Elena Grigorescu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Young-San Lin</a>, <a href="/search/cs?searchtype=author&query=Song%2C+M">Maoyuan Song</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="2411.08332v1-abstract-short" style="display: inline;"> Learning-augmented algorithms have been extensively studied across the computer science community in the recent years, driven by advances in machine learning predictors, which can provide additional information to augment classical algorithms. Such predictions are especially powerful in the context of online problems, where decisions have to be made without knowledge of the future, and which tradi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08332v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08332v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08332v1-abstract-full" style="display: none;"> Learning-augmented algorithms have been extensively studied across the computer science community in the recent years, driven by advances in machine learning predictors, which can provide additional information to augment classical algorithms. Such predictions are especially powerful in the context of online problems, where decisions have to be made without knowledge of the future, and which traditionally exhibits impossibility results bounding the performance of any online algorithm. The study of learning-augmented algorithms thus aims to use external advice prudently, to overcome classical impossibility results when the advice is accurate, and still perform comparably to the state-of-the-art online algorithms even when the advice is inaccurate. In this paper, we present learning-augmented algorithmic frameworks for two fundamental optimizations settings, extending and generalizing prior works. For online packing with concave objectives, we present a simple but overarching strategy that switches between the advice and the state-of-the-art online algorithm. For online covering with convex objectives, we greatly extend primal-dual methods for online convex covering programs by Azar et al. (FOCS 2016) and previous learning-augmented framework for online covering linear programs from the literature, to many new applications. We show that our algorithms break impossibility results when the advice is accurate, while maintaining comparable performance with state-of-the-art classical online algorithms even when the advice is erroneous. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08332v1-abstract-full').style.display = 'none'; document.getElementById('2411.08332v1-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> <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">38 pages. In submission</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07135">arXiv:2411.07135</a> <span> [<a href="https://arxiv.org/pdf/2411.07135">pdf</a>, <a href="https://arxiv.org/format/2411.07135">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> </div> </div> <p class="title is-5 mathjax"> Edify 3D: Scalable High-Quality 3D Asset Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=NVIDIA"> NVIDIA</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Bala%2C+M">Maciej Bala</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Y">Yin Cui</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yifan Ding</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+Y">Yunhao Ge</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Z">Zekun Hao</a>, <a href="/search/cs?searchtype=author&query=Hasselgren%2C+J">Jon Hasselgren</a>, <a href="/search/cs?searchtype=author&query=Huffman%2C+J">Jacob Huffman</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+J">Jingyi Jin</a>, <a href="/search/cs?searchtype=author&query=Lewis%2C+J+P">J. P. Lewis</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhaoshuo Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chen-Hsuan Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yen-Chen Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Tsung-Yi Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Ming-Yu Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+A">Alice Luo</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Q">Qianli Ma</a>, <a href="/search/cs?searchtype=author&query=Munkberg%2C+J">Jacob Munkberg</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+S">Stella Shi</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+F">Fangyin Wei</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+D">Donglai Xiang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiashu Xu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+X">Xiaohui Zeng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qinsheng 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="2411.07135v1-abstract-short" style="display: inline;"> We introduce Edify 3D, an advanced solution designed for high-quality 3D asset generation. Our method first synthesizes RGB and surface normal images of the described object at multiple viewpoints using a diffusion model. The multi-view observations are then used to reconstruct the shape, texture, and PBR materials of the object. Our method can generate high-quality 3D assets with detailed geometr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07135v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07135v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07135v1-abstract-full" style="display: none;"> We introduce Edify 3D, an advanced solution designed for high-quality 3D asset generation. Our method first synthesizes RGB and surface normal images of the described object at multiple viewpoints using a diffusion model. The multi-view observations are then used to reconstruct the shape, texture, and PBR materials of the object. Our method can generate high-quality 3D assets with detailed geometry, clean shape topologies, high-resolution textures, and materials within 2 minutes of runtime. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07135v1-abstract-full').style.display = 'none'; document.getElementById('2411.07135v1-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">Project website: https://research.nvidia.com/labs/dir/edify-3d</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07133">arXiv:2411.07133</a> <span> [<a href="https://arxiv.org/pdf/2411.07133">pdf</a>, <a href="https://arxiv.org/format/2411.07133">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> </div> </div> <p class="title is-5 mathjax"> Stronger Models are NOT Stronger Teachers for Instruction Tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhangchen Xu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+F">Fengqing Jiang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+B+Y">Bill Yuchen Lin</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2411.07133v2-abstract-short" style="display: inline;"> Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs heavily rely on the instruction datasets used for tuning. Recently, synthetic instruction datasets have emerged as an economically viable solution to provide LLMs diverse and high-quality instructions. However, existing app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07133v2-abstract-full').style.display = 'inline'; document.getElementById('2411.07133v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07133v2-abstract-full" style="display: none;"> Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs heavily rely on the instruction datasets used for tuning. Recently, synthetic instruction datasets have emerged as an economically viable solution to provide LLMs diverse and high-quality instructions. However, existing approaches typically assume that larger or stronger models are stronger teachers for instruction tuning, and hence simply adopt these models as response generators to the synthetic instructions. In this paper, we challenge this commonly-adopted assumption. Our extensive experiments across five base models and twenty response generators reveal that larger and stronger models are not necessarily stronger teachers of smaller models. We refer to this phenomenon as the Larger Models' Paradox. We observe that existing metrics cannot precisely predict the effectiveness of response generators since they ignore the compatibility between teachers and base models being fine-tuned. We thus develop a novel metric, named as Compatibility-Adjusted Reward (CAR) to measure the effectiveness of response generators. Our experiments across five base models demonstrate that CAR outperforms almost all baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07133v2-abstract-full').style.display = 'none'; document.getElementById('2411.07133v2-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">v1</span> submitted 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07126">arXiv:2411.07126</a> <span> [<a href="https://arxiv.org/pdf/2411.07126">pdf</a>, <a href="https://arxiv.org/format/2411.07126">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=NVIDIA"> NVIDIA</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Atzmon%2C+Y">Yuval Atzmon</a>, <a href="/search/cs?searchtype=author&query=Bala%2C+M">Maciej Bala</a>, <a href="/search/cs?searchtype=author&query=Balaji%2C+Y">Yogesh Balaji</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+T">Tiffany Cai</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Y">Yin Cui</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+J">Jiaojiao Fan</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+Y">Yunhao Ge</a>, <a href="/search/cs?searchtype=author&query=Gururani%2C+S">Siddharth Gururani</a>, <a href="/search/cs?searchtype=author&query=Huffman%2C+J">Jacob Huffman</a>, <a href="/search/cs?searchtype=author&query=Isaac%2C+R">Ronald Isaac</a>, <a href="/search/cs?searchtype=author&query=Jannaty%2C+P">Pooya Jannaty</a>, <a href="/search/cs?searchtype=author&query=Karras%2C+T">Tero Karras</a>, <a href="/search/cs?searchtype=author&query=Lam%2C+G">Grace Lam</a>, <a href="/search/cs?searchtype=author&query=Lewis%2C+J+P">J. P. Lewis</a>, <a href="/search/cs?searchtype=author&query=Licata%2C+A">Aaron Licata</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yen-Chen Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Ming-Yu Liu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Q">Qianli Ma</a>, <a href="/search/cs?searchtype=author&query=Mallya%2C+A">Arun Mallya</a>, <a href="/search/cs?searchtype=author&query=Martino-Tarr%2C+A">Ashlee Martino-Tarr</a>, <a href="/search/cs?searchtype=author&query=Mendez%2C+D">Doug Mendez</a>, <a href="/search/cs?searchtype=author&query=Nah%2C+S">Seungjun Nah</a>, <a href="/search/cs?searchtype=author&query=Pruett%2C+C">Chris Pruett</a> , et al. (7 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="2411.07126v1-abstract-short" style="display: inline;"> We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07126v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07126v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07126v1-abstract-full" style="display: none;"> We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360 HDR panorama generation, and finetuning for image customization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07126v1-abstract-full').style.display = 'none'; document.getElementById('2411.07126v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07111">arXiv:2411.07111</a> <span> [<a href="https://arxiv.org/pdf/2411.07111">pdf</a>, <a href="https://arxiv.org/format/2411.07111">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="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"> Building a Taiwanese Mandarin Spoken Language Model: A First Attempt </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chih-Kai Yang</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yu-Kuan Fu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chen-An Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yi-Cheng Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yu-Xiang Lin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei-Chih Chen</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+H+L">Ho Lam Chung</a>, <a href="/search/cs?searchtype=author&query=Kuan%2C+C">Chun-Yi Kuan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wei-Ping Huang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+K">Ke-Han Lu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Tzu-Quan Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hsiu-Hsuan Wang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+E">En-Pei Hu</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+C">Chan-Jan Hsu</a>, <a href="/search/cs?searchtype=author&query=Tseng%2C+L">Liang-Hsuan Tseng</a>, <a href="/search/cs?searchtype=author&query=Chiu%2C+I">I-Hsiang Chiu</a>, <a href="/search/cs?searchtype=author&query=Sanga%2C+U">Ulin Sanga</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuanjun Chen</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+P">Po-chun Hsu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shu-wen Yang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+H">Hung-yi Lee</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="2411.07111v1-abstract-short" style="display: inline;"> This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07111v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07111v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07111v1-abstract-full" style="display: none;"> This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex capabilities allowing simultaneous speaking and listening. The paper also details the training process, including data preparation with synthesized dialogues and adjustments for real-time interaction. We also developed a platform to evaluate conversational fluency and response coherence in multi-turn dialogues. We hope the release of the report can contribute to the future development of spoken LLMs in Taiwanese Mandarin. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07111v1-abstract-full').style.display = 'none'; document.getElementById('2411.07111v1-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">Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07076">arXiv:2411.07076</a> <span> [<a href="https://arxiv.org/pdf/2411.07076">pdf</a>, <a href="https://arxiv.org/format/2411.07076">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"> StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+Y">Yichen He</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yuan Lin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jianchao Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hanchong Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Le%2C+R">Ruicheng Le</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07076v1-abstract-short" style="display: inline;"> Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as plot-level consistency across descriptions. To address these, we figure out audio-visual character identification, matching character names… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07076v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07076v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07076v1-abstract-full" style="display: none;"> Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as plot-level consistency across descriptions. To address these, we figure out audio-visual character identification, matching character names to each dialogue, as a key factor. We propose StoryTeller, a system for generating dense descriptions of long videos, incorporating both low-level visual concepts and high-level plot information. StoryTeller uses a multimodal large language model that integrates visual, audio, and text modalities to perform audio-visual character identification on minute-long video clips. The results are then fed into a LVLM to enhance consistency of video description. We validate our approach on movie description tasks and introduce MovieStory101, a dataset with dense descriptions for three-minute movie clips. To evaluate long video descriptions, we create MovieQA, a large set of multiple-choice questions for the MovieStory101 test set. We assess descriptions by inputting them into GPT-4 to answer these questions, using accuracy as an automatic evaluation metric. Experiments show that StoryTeller outperforms all open and closed-source baselines on MovieQA, achieving 9.5% higher accuracy than the strongest baseline, Gemini-1.5-pro, and demonstrating a +15.56% advantage in human side-by-side evaluations. Additionally, incorporating audio-visual character identification from StoryTeller improves the performance of all video description models, with Gemini-1.5-pro and GPT-4o showing relative improvement of 5.5% and 13.0%, respectively, in accuracy on MovieQA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07076v1-abstract-full').style.display = 'none'; document.getElementById('2411.07076v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06427">arXiv:2411.06427</a> <span> [<a href="https://arxiv.org/pdf/2411.06427">pdf</a>, <a href="https://arxiv.org/format/2411.06427">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"> UniGAD: Unifying Multi-level Graph Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiqing Lin</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jianheng Tang</a>, <a href="/search/cs?searchtype=author&query=Zi%2C+C">Chenyi Zi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H+V">H. Vicky Zhao</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yuan Yao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jia 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="2411.06427v1-abstract-short" style="display: inline;"> Graph Anomaly Detection (GAD) aims to identify uncommon, deviated, or suspicious objects within graph-structured data. Existing methods generally focus on a single graph object type (node, edge, graph, etc.) and often overlook the inherent connections among different object types of graph anomalies. For instance, a money laundering transaction might involve an abnormal account and the broader comm… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06427v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06427v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06427v1-abstract-full" style="display: none;"> Graph Anomaly Detection (GAD) aims to identify uncommon, deviated, or suspicious objects within graph-structured data. Existing methods generally focus on a single graph object type (node, edge, graph, etc.) and often overlook the inherent connections among different object types of graph anomalies. For instance, a money laundering transaction might involve an abnormal account and the broader community it interacts with. To address this, we present UniGAD, the first unified framework for detecting anomalies at node, edge, and graph levels jointly. Specifically, we develop the Maximum Rayleigh Quotient Subgraph Sampler (MRQSampler) that unifies multi-level formats by transferring objects at each level into graph-level tasks on subgraphs. We theoretically prove that MRQSampler maximizes the accumulated spectral energy of subgraphs (i.e., the Rayleigh quotient) to preserve the most significant anomaly information. To further unify multi-level training, we introduce a novel GraphStitch Network to integrate information across different levels, adjust the amount of sharing required at each level, and harmonize conflicting training goals. Comprehensive experiments show that UniGAD outperforms both existing GAD methods specialized for a single task and graph prompt-based approaches for multiple tasks, while also providing robust zero-shot task transferability. All codes can be found at https://github.com/lllyyq1121/UniGAD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06427v1-abstract-full').style.display = 'none'; document.getElementById('2411.06427v1-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">Accepted by NeurIPS 2024. All codes can be found at https://github.com/lllyyq1121/UniGAD</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06391">arXiv:2411.06391</a> <span> [<a href="https://arxiv.org/pdf/2411.06391">pdf</a>, <a href="https://arxiv.org/format/2411.06391">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="Computational Engineering, Finance, and Science">cs.CE</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"> CausalStock: Deep End-to-end Causal Discovery for News-driven Stock Movement Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuqi Li</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yuebo Sun</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yuxin Lin</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xin Gao</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+S">Shuo Shang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+R">Rui Yan</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="2411.06391v1-abstract-short" style="display: inline;"> There are two issues in news-driven multi-stock movement prediction tasks that are not well solved in the existing works. On the one hand, "relation discovery" is a pivotal part when leveraging the price information of other stocks to achieve accurate stock movement prediction. Given that stock relations are often unidirectional, such as the "supplier-consumer" relationship, causal relations are m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06391v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06391v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06391v1-abstract-full" style="display: none;"> There are two issues in news-driven multi-stock movement prediction tasks that are not well solved in the existing works. On the one hand, "relation discovery" is a pivotal part when leveraging the price information of other stocks to achieve accurate stock movement prediction. Given that stock relations are often unidirectional, such as the "supplier-consumer" relationship, causal relations are more appropriate to capture the impact between stocks. On the other hand, there is substantial noise existing in the news data leading to extracting effective information with difficulty. With these two issues in mind, we propose a novel framework called CausalStock for news-driven multi-stock movement prediction, which discovers the temporal causal relations between stocks. We design a lag-dependent temporal causal discovery mechanism to model the temporal causal graph distribution. Then a Functional Causal Model is employed to encapsulate the discovered causal relations and predict the stock movements. Additionally, we propose a Denoised News Encoder by taking advantage of the excellent text evaluation ability of large language models (LLMs) to extract useful information from massive news data. The experiment results show that CausalStock outperforms the strong baselines for both news-driven multi-stock movement prediction and multi-stock movement prediction tasks on six real-world datasets collected from the US, China, Japan, and UK markets. Moreover, getting benefit from the causal relations, CausalStock could offer a clear prediction mechanism with good explainability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06391v1-abstract-full').style.display = 'none'; document.getElementById('2411.06391v1-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">Accepted by 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/2411.05945">arXiv:2411.05945</a> <span> [<a href="https://arxiv.org/pdf/2411.05945">pdf</a>, <a href="https://arxiv.org/format/2411.05945">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yen-Ting Lin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C+H">Chao-Han Huck Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhehuai Chen</a>, <a href="/search/cs?searchtype=author&query=Zelasko%2C+P">Piotr Zelasko</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xuesong Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zih-Ching Chen</a>, <a href="/search/cs?searchtype=author&query=Puvvada%2C+K+C">Krishna C Puvvada</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+S">Szu-Wei Fu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+K">Ke Hu</a>, <a href="/search/cs?searchtype=author&query=Chiu%2C+J+W">Jun Wei Chiu</a>, <a href="/search/cs?searchtype=author&query=Balam%2C+J">Jagadeesh Balam</a>, <a href="/search/cs?searchtype=author&query=Ginsburg%2C+B">Boris Ginsburg</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y+F">Yu-Chiang Frank 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="2411.05945v1-abstract-short" style="display: inline;"> Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05945v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05945v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05945v1-abstract-full" style="display: none;"> Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative $5.0$% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with $15.5$% to $27.6$% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05945v1-abstract-full').style.display = 'none'; document.getElementById('2411.05945v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 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">NeKo work has been done in June 2024. NeKo LMs will be open source on https://huggingface.co/nvidia under the MIT license</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05451">arXiv:2411.05451</a> <span> [<a href="https://arxiv.org/pdf/2411.05451">pdf</a>, <a href="https://arxiv.org/format/2411.05451">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fan%2C+S">Shengda Fan</a>, <a href="/search/cs?searchtype=author&query=Cong%2C+X">Xin Cong</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yuepeng Fu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhong Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shuyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuanwei Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yesai Wu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yankai Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+M">Maosong Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05451v1-abstract-short" style="display: inline;"> Recent advancements in large language models (LLMs) have driven a revolutionary paradigm shift in process automation from Robotic Process Automation to Agentic Process Automation by automating the workflow orchestration procedure based on LLMs. However, existing LLMs (even the advanced OpenAI GPT-4o) are confined to achieving satisfactory capability in workflow orchestration. To address this limit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05451v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05451v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05451v1-abstract-full" style="display: none;"> Recent advancements in large language models (LLMs) have driven a revolutionary paradigm shift in process automation from Robotic Process Automation to Agentic Process Automation by automating the workflow orchestration procedure based on LLMs. However, existing LLMs (even the advanced OpenAI GPT-4o) are confined to achieving satisfactory capability in workflow orchestration. To address this limitation, we present WorkflowLLM, a data-centric framework elaborately designed to enhance the capability of LLMs in workflow orchestration. It first constructs a large-scale fine-tuning dataset WorkflowBench with 106,763 samples, covering 1,503 APIs from 83 applications across 28 categories. Specifically, the construction process can be divided into three phases: (1) Data Collection: we collect real-world workflow data from Apple Shortcuts and RoutineHub, transcribing them into Python-style code. We further equip them with generated hierarchical thought via ChatGPT. (2) Query Expansion: we prompt ChatGPT to generate more task queries to enrich the diversity and complexity of workflows. (3) Workflow Generation: we leverage an annotator model trained on collected data to generate workflows for synthesized queries. Finally, we merge the synthetic samples that pass quality confirmation with the collected samples to obtain the WorkflowBench. Based on WorkflowBench, we fine-tune Llama-3.1-8B to obtain WorkflowLlama. Our experiments show that WorkflowLlama demonstrates a strong capacity to orchestrate complex workflows, while also achieving notable generalization performance on previously unseen APIs. Additionally, WorkflowBench exhibits robust zero-shot generalization capabilities on an out-of-distribution task planning dataset, T-Eval. Our data and code are available at https://github.com/OpenBMB/WorkflowLLM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05451v1-abstract-full').style.display = 'none'; document.getElementById('2411.05451v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 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/2411.05361">arXiv:2411.05361</a> <span> [<a href="https://arxiv.org/pdf/2411.05361">pdf</a>, <a href="https://arxiv.org/format/2411.05361">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="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+C">Chien-yu Huang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei-Chih Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shu-wen Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A+T">Andy T. Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chen-An Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yu-Xiang Lin</a>, <a href="/search/cs?searchtype=author&query=Tseng%2C+W">Wei-Cheng Tseng</a>, <a href="/search/cs?searchtype=author&query=Diwan%2C+A">Anuj Diwan</a>, <a href="/search/cs?searchtype=author&query=Shih%2C+Y">Yi-Jen Shih</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jiatong Shi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">William Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuanjun Chen</a>, <a href="/search/cs?searchtype=author&query=Hsiao%2C+C">Chi-Yuan Hsiao</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+P">Puyuan Peng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shih-Heng Wang</a>, <a href="/search/cs?searchtype=author&query=Kuan%2C+C">Chun-Yi Kuan</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+K">Ke-Han Lu</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K">Kai-Wei Chang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chih-Kai Yang</a>, <a href="/search/cs?searchtype=author&query=Ritter-Gutierrez%2C+F">Fabian Ritter-Gutierrez</a>, <a href="/search/cs?searchtype=author&query=Chuang%2C+M+T">Ming To Chuang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+K">Kuan-Po Huang</a>, <a href="/search/cs?searchtype=author&query=Arora%2C+S">Siddhant Arora</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">You-Kuan Lin</a>, <a href="/search/cs?searchtype=author&query=Yeo%2C+E">Eunjung Yeo</a> , et al. (53 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="2411.05361v1-abstract-short" style="display: inline;"> Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05361v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05361v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05361v1-abstract-full" style="display: none;"> Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results indicate that none of the models performed well universally. SALMONN-13B excelled in English ASR, while WavLLM demonstrated high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We will soon open-source all task data and the evaluation pipeline. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05361v1-abstract-full').style.display = 'none'; document.getElementById('2411.05361v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 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/2411.05349">arXiv:2411.05349</a> <span> [<a href="https://arxiv.org/pdf/2411.05349">pdf</a>, <a href="https://arxiv.org/format/2411.05349">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Cluster Resilience: LLM-agent Based Autonomous Intelligent Cluster Diagnosis System and Evaluation Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+H">Honghao Shi</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Longkai Cheng</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+W">Wenli Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuhang Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xuan Liu</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+S">Shaokai Nie</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weixv Wang</a>, <a href="/search/cs?searchtype=author&query=Min%2C+X">Xuebin Min</a>, <a href="/search/cs?searchtype=author&query=Men%2C+C">Chunlei Men</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yonghua Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05349v1-abstract-short" style="display: inline;"> Recent advancements in Large Language Models (LLMs) and related technologies such as Retrieval-Augmented Generation (RAG) and Diagram of Thought (DoT) have enabled the creation of autonomous intelligent systems capable of performing cluster diagnostics and troubleshooting. By integrating these technologies with self-play methodologies, we have developed an LLM-agent system designed to autonomously… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05349v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05349v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05349v1-abstract-full" style="display: none;"> Recent advancements in Large Language Models (LLMs) and related technologies such as Retrieval-Augmented Generation (RAG) and Diagram of Thought (DoT) have enabled the creation of autonomous intelligent systems capable of performing cluster diagnostics and troubleshooting. By integrating these technologies with self-play methodologies, we have developed an LLM-agent system designed to autonomously diagnose and resolve issues within AI clusters. Our innovations include a knowledge base tailored for cluster diagnostics, enhanced LLM algorithms, practical deployment strategies for agents, and a benchmark specifically designed for evaluating LLM capabilities in this domain. Through extensive experimentation across multiple dimensions, we have demonstrated the superiority of our system in addressing the challenges faced in cluster diagnostics, particularly in detecting and rectifying performance issues more efficiently and accurately than traditional methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05349v1-abstract-full').style.display = 'none'; document.getElementById('2411.05349v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 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">10 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T42 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05335">arXiv:2411.05335</a> <span> [<a href="https://arxiv.org/pdf/2411.05335">pdf</a>, <a href="https://arxiv.org/format/2411.05335">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A Quality-Centric Framework for Generic Deepfake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Song%2C+W">Wentang Song</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zhiyuan Yan</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yuzhen Lin</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Taiping Yao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Changsheng Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shen Chen</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yandan Zhao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+S">Shouhong Ding</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bin 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="2411.05335v1-abstract-short" style="display: inline;"> This paper addresses the generalization issue in deepfake detection by harnessing forgery quality in training data. Generally, the forgery quality of different deepfakes varies: some have easily recognizable forgery clues, while others are highly realistic. Existing works often train detectors on a mix of deepfakes with varying forgery qualities, potentially leading detectors to short-cut the easy… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05335v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05335v1-abstract-full" style="display: none;"> This paper addresses the generalization issue in deepfake detection by harnessing forgery quality in training data. Generally, the forgery quality of different deepfakes varies: some have easily recognizable forgery clues, while others are highly realistic. Existing works often train detectors on a mix of deepfakes with varying forgery qualities, potentially leading detectors to short-cut the easy-to-spot artifacts from low-quality forgery samples, thereby hurting generalization performance. To tackle this issue, we propose a novel quality-centric framework for generic deepfake detection, which is composed of a Quality Evaluator, a low-quality data enhancement module, and a learning pacing strategy that explicitly incorporates forgery quality into the training process. The framework is inspired by curriculum learning, which is designed to gradually enable the detector to learn more challenging deepfake samples, starting with easier samples and progressing to more realistic ones. We employ both static and dynamic assessments to assess the forgery quality, combining their scores to produce a final rating for each training sample. The rating score guides the selection of deepfake samples for training, with higher-rated samples having a higher probability of being chosen. Furthermore, we propose a novel frequency data augmentation method specifically designed for low-quality forgery samples, which helps to reduce obvious forgery traces and improve their overall realism. Extensive experiments show that our method can be applied in a plug-and-play manner and significantly enhance the generalization performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05335v1-abstract-full').style.display = 'none'; document.getElementById('2411.05335v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 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/2411.05007">arXiv:2411.05007</a> <span> [<a href="https://arxiv.org/pdf/2411.05007">pdf</a>, <a href="https://arxiv.org/format/2411.05007">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+M">Muyang Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yujun Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhekai Zhang</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+T">Tianle Cai</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiuyu Li</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Junxian Guo</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+E">Enze Xie</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+C">Chenlin Meng</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jun-Yan Zhu</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S">Song 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="2411.05007v2-abstract-short" style="display: inline;"> Diffusion models have been proven highly effective at generating high-quality images. However, as these models grow larger, they require significantly more memory and suffer from higher latency, posing substantial challenges for deployment. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits. At such an aggressive level, both weights and activa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05007v2-abstract-full').style.display = 'inline'; document.getElementById('2411.05007v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05007v2-abstract-full" style="display: none;"> Diffusion models have been proven highly effective at generating high-quality images. However, as these models grow larger, they require significantly more memory and suffer from higher latency, posing substantial challenges for deployment. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits. At such an aggressive level, both weights and activations are highly sensitive, where conventional post-training quantization methods for large language models like smoothing become insufficient. To overcome this limitation, we propose SVDQuant, a new 4-bit quantization paradigm. Different from smoothing which redistributes outliers between weights and activations, our approach absorbs these outliers using a low-rank branch. We first consolidate the outliers by shifting them from activations to weights, then employ a high-precision low-rank branch to take in the weight outliers with Singular Value Decomposition (SVD). This process eases the quantization on both sides. However, na茂vely running the low-rank branch independently incurs significant overhead due to extra data movement of activations, negating the quantization speedup. To address this, we co-design an inference engine Nunchaku that fuses the kernels of the low-rank branch into those of the low-bit branch to cut off redundant memory access. It can also seamlessly support off-the-shelf low-rank adapters (LoRAs) without the need for re-quantization. Extensive experiments on SDXL, PixArt-$危$, and FLUX.1 validate the effectiveness of SVDQuant in preserving image quality. We reduce the memory usage for the 12B FLUX.1 models by 3.5$\times$, achieving 3.0$\times$ speedup over the 4-bit weight-only quantized baseline on the 16GB laptop 4090 GPU, paving the way for more interactive applications on PCs. Our quantization library and inference engine are open-sourced. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05007v2-abstract-full').style.display = 'none'; document.getElementById('2411.05007v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <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">Quantization Library: https://github.com/mit-han-lab/deepcompressor Inference Engine: https://github.com/mit-han-lab/nunchaku Website: https://hanlab.mit.edu/projects/svdquant Demo: https://svdquant.mit.edu Blog: https://hanlab.mit.edu/blog/svdquant</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01465">arXiv:2411.01465</a> <span> [<a href="https://arxiv.org/pdf/2411.01465">pdf</a>, <a href="https://arxiv.org/format/2411.01465">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"> Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bai%2C+L">Liang Bai</a>, <a href="/search/cs?searchtype=author&query=Song%2C+H">Hong Song</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yucong Lin</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+T">Tianyu Fu</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+D">Deqiang Xiao</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+D">Danni Ai</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+J">Jingfan Fan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian 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="2411.01465v1-abstract-short" style="display: inline;"> Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scenarios. Current Non-Exemplar Class-Incremental Learning (NECIL) methods mitigate forgetting by storing a single prototype per class, which serves to inject previous information when sequentially learning new classes. Howe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01465v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01465v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01465v1-abstract-full" style="display: none;"> Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scenarios. Current Non-Exemplar Class-Incremental Learning (NECIL) methods mitigate forgetting by storing a single prototype per class, which serves to inject previous information when sequentially learning new classes. However, these stored prototypes or their augmented variants often fail to simultaneously capture spatial distribution diversity and precision needed for representing old classes. Moreover, as the model acquires new knowledge, these prototypes gradually become outdated, making them less effective. To overcome these limitations, we propose a more efficient NECIL method that replaces prototypes with synthesized retrospective features for old classes. Specifically, we model each old class's feature space using a multivariate Gaussian distribution and generate deep representations by sampling from high-likelihood regions. Additionally, we introduce a similarity-based feature compensation mechanism that integrates generated old class features with similar new class features to synthesize robust retrospective representations. These retrospective features are then incorporated into our incremental learning framework to preserve the decision boundaries of previous classes while learning new ones. Extensive experiments on CIFAR-100, TinyImageNet, and ImageNet-Subset demonstrate that our method significantly improves the efficiency of non-exemplar class-incremental learning and achieves state-of-the-art performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01465v1-abstract-full').style.display = 'none'; document.getElementById('2411.01465v1-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">13 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/2411.00823">arXiv:2411.00823</a> <span> [<a href="https://arxiv.org/pdf/2411.00823">pdf</a>, <a href="https://arxiv.org/format/2411.00823">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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gong%2C+L">Letian Gong</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinyue Zhang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yiwen Lu</a>, <a href="/search/cs?searchtype=author&query=Han%2C+X">Xuedi Han</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yichen Liu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2411.00823v1-abstract-short" style="display: inline;"> Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00823v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00823v1-abstract-full" style="display: none;"> Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to an incomplete comprehension. Drawing inspiration from the exceptional semantic understanding and contextual information processing capabilities of large language models (LLMs) across various domains, we present Mobility-LLM, a novel framework that leverages LLMs to analyze check-in sequences for multiple tasks. Since LLMs cannot directly interpret check-ins, we reprogram these sequences to help LLMs comprehensively understand the semantics of human visiting intentions and travel preferences. Specifically, we introduce a visiting intention memory network (VIMN) to capture the visiting intentions at each record, along with a shared pool of human travel preference prompts (HTPP) to guide the LLM in understanding users' travel preferences. These components enhance the model's ability to extract and leverage semantic information from human mobility data effectively. Extensive experiments on four benchmark datasets and three downstream tasks demonstrate that our approach significantly outperforms existing models, underscoring the effectiveness of Mobility-LLM in advancing our understanding of human mobility data within LBS contexts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00823v1-abstract-full').style.display = 'none'; document.getElementById('2411.00823v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00653">arXiv:2411.00653</a> <span> [<a href="https://arxiv.org/pdf/2411.00653">pdf</a>, <a href="https://arxiv.org/format/2411.00653">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"> Rethinking Node Representation Interpretation through Relation Coherence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Ying-Chun Lin</a>, <a href="/search/cs?searchtype=author&query=Neville%2C+J">Jennifer Neville</a>, <a href="/search/cs?searchtype=author&query=Becker%2C+C">Cassiano Becker</a>, <a href="/search/cs?searchtype=author&query=Metha%2C+P">Purvanshi Metha</a>, <a href="/search/cs?searchtype=author&query=Asghar%2C+N">Nabiha Asghar</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+V">Vipul Agarwal</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="2411.00653v1-abstract-short" style="display: inline;"> Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00653v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00653v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00653v1-abstract-full" style="display: none;"> Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research that focuses on interpretation lacks validation, and thus the reliability of such methods is unclear. We address this gap by proposing a novel interpretation method-Node Coherence Rate for Representation Interpretation (NCI)-which quantifies how well different node relations are captured in node representations. We also propose a novel method (IME) to evaluate the accuracy of different interpretation methods. Our experimental results demonstrate that NCI reduces the error of the previous best approach by an average of 39%. We then apply NCI to derive insights about the node representations produced by several graph-based methods and assess their quality in unsupervised settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00653v1-abstract-full').style.display = 'none'; document.getElementById('2411.00653v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 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/2411.00604">arXiv:2411.00604</a> <span> [<a href="https://arxiv.org/pdf/2411.00604">pdf</a>, <a href="https://arxiv.org/format/2411.00604">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"> ConvCounsel: A Conversational Dataset for Student Counseling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+P">Po-Chuan Chen</a>, <a href="/search/cs?searchtype=author&query=Rohmatillah%2C+M">Mahdin Rohmatillah</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">You-Teng Lin</a>, <a href="/search/cs?searchtype=author&query=Chien%2C+J">Jen-Tzung Chien</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="2411.00604v1-abstract-short" style="display: inline;"> Student mental health is a sensitive issue that necessitates special attention. A primary concern is the student-to-counselor ratio, which surpasses the recommended standard of 250:1 in most universities. This imbalance results in extended waiting periods for in-person consultations, which cause suboptimal treatment. Significant efforts have been directed toward developing mental health dialogue s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00604v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00604v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00604v1-abstract-full" style="display: none;"> Student mental health is a sensitive issue that necessitates special attention. A primary concern is the student-to-counselor ratio, which surpasses the recommended standard of 250:1 in most universities. This imbalance results in extended waiting periods for in-person consultations, which cause suboptimal treatment. Significant efforts have been directed toward developing mental health dialogue systems utilizing the existing open-source mental health-related datasets. However, currently available datasets either discuss general topics or various strategies that may not be viable for direct application due to numerous ethical constraints inherent in this research domain. To address this issue, this paper introduces a specialized mental health dataset that emphasizes the active listening strategy employed in conversation for counseling, also named as ConvCounsel. This dataset comprises both speech and text data, which can facilitate the development of a reliable pipeline for mental health dialogue systems. To demonstrate the utility of the proposed dataset, this paper also presents the NYCUKA, a spoken mental health dialogue system that is designed by using the ConvCounsel dataset. The results show the merit of using this dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00604v1-abstract-full').style.display = 'none'; document.getElementById('2411.00604v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 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 at O-COCOSDA 2024, Won Best Student Paper Award</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00078">arXiv:2411.00078</a> <span> [<a href="https://arxiv.org/pdf/2411.00078">pdf</a>, <a href="https://arxiv.org/format/2411.00078">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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/cs?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/cs?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yuankai Huo</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="2411.00078v1-abstract-short" style="display: inline;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei seg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00078v1-abstract-full" style="display: none;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei segmentation within a single organ (e.g., the kidney), remains uncertain. This paper seeks to answer this key question, "How good are we?", by thoroughly evaluating the performance of recent cell foundation models on a curated multi-center, multi-disease, and multi-species external testing dataset. Additionally, we tackle a more challenging question, "How can we improve?", by developing and assessing human-in-the-loop data enrichment strategies aimed at enhancing model performance while minimizing the reliance on pixel-level human annotation. To address the first question, we curated a multicenter, multidisease, and multispecies dataset consisting of 2,542 kidney whole slide images (WSIs). Three state-of-the-art (SOTA) cell foundation models-Cellpose, StarDist, and CellViT-were selected for evaluation. To tackle the second question, we explored data enrichment algorithms by distilling predictions from the different foundation models with a human-in-the-loop framework, aiming to further enhance foundation model performance with minimal human efforts. Our experimental results showed that all three foundation models improved over their baselines with model fine-tuning with enriched data. Interestingly, the baseline model with the highest F1 score does not yield the best segmentation outcomes after fine-tuning. This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'none'; document.getElementById('2411.00078v1-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/2410.23715">arXiv:2410.23715</a> <span> [<a href="https://arxiv.org/pdf/2410.23715">pdf</a>, <a href="https://arxiv.org/format/2410.23715">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> <p class="title is-5 mathjax"> Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Song%2C+J">Jia Song</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+W">Wanru Zhuang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yujie Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Liang Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunyan Li</a>, <a href="/search/cs?searchtype=author&query=Su%2C+J">Jinsong Su</a>, <a href="/search/cs?searchtype=author&query=He%2C+S">Song He</a>, <a href="/search/cs?searchtype=author&query=Bo%2C+X">Xiaochen Bo</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="2410.23715v1-abstract-short" style="display: inline;"> Cross-modal text-molecule retrieval model aims to learn a shared feature space of the text and molecule modalities for accurate similarity calculation, which facilitates the rapid screening of molecules with specific properties and activities in drug design. However, previous works have two main defects. First, they are inadequate in capturing modality-shared features considering the significant g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23715v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23715v1-abstract-full" style="display: none;"> Cross-modal text-molecule retrieval model aims to learn a shared feature space of the text and molecule modalities for accurate similarity calculation, which facilitates the rapid screening of molecules with specific properties and activities in drug design. However, previous works have two main defects. First, they are inadequate in capturing modality-shared features considering the significant gap between text sequences and molecule graphs. Second, they mainly rely on contrastive learning and adversarial training for cross-modality alignment, both of which mainly focus on the first-order similarity, ignoring the second-order similarity that can capture more structural information in the embedding space. To address these issues, we propose a novel cross-modal text-molecule retrieval model with two-fold improvements. Specifically, on the top of two modality-specific encoders, we stack a memory bank based feature projector that contain learnable memory vectors to extract modality-shared features better. More importantly, during the model training, we calculate four kinds of similarity distributions (text-to-text, text-to-molecule, molecule-to-molecule, and molecule-to-text similarity distributions) for each instance, and then minimize the distance between these similarity distributions (namely second-order similarity losses) to enhance cross-modal alignment. Experimental results and analysis strongly demonstrate the effectiveness of our model. Particularly, our model achieves SOTA performance, outperforming the previously-reported best result by 6.4%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23715v1-abstract-full').style.display = 'none'; document.getElementById('2410.23715v1-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">BIBM 2024 regular paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23123">arXiv:2410.23123</a> <span> [<a href="https://arxiv.org/pdf/2410.23123">pdf</a>, <a href="https://arxiv.org/format/2410.23123">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"> On Memorization of Large Language Models in Logical Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xie%2C+C">Chulin Xie</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yangsibo Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chiyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Da Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyun Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+B+Y">Bill Yuchen Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bo Li</a>, <a href="/search/cs?searchtype=author&query=Ghazi%2C+B">Badih Ghazi</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+R">Ravi Kumar</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="2410.23123v1-abstract-short" style="display: inline;"> Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabilities. One hypothesis is that the increasingly high and nearly saturated performance on common reasoning benchmarks could be due to the memorization… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23123v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23123v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23123v1-abstract-full" style="display: none;"> Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabilities. One hypothesis is that the increasingly high and nearly saturated performance on common reasoning benchmarks could be due to the memorization of similar problems. In this paper, we systematically investigate this hypothesis with a quantitative measurement of memorization in reasoning tasks, using a dynamically generated logical reasoning benchmark based on Knights and Knaves (K&K) puzzles. We found that LLMs could interpolate the training puzzles (achieving near-perfect accuracy) after fine-tuning, yet fail when those puzzles are slightly perturbed, suggesting that the models heavily rely on memorization to solve those training puzzles. On the other hand, we show that while fine-tuning leads to heavy memorization, it also consistently improves generalization performance. In-depth analyses with perturbation tests, cross difficulty-level transferability, probing model internals, and fine-tuning with wrong answers suggest that the LLMs learn to reason on K&K puzzles despite training data memorization. This phenomenon indicates that LLMs exhibit a complex interplay between memorization and genuine reasoning abilities. Finally, our analysis with per-sample memorization score sheds light on how LLMs switch between reasoning and memorization in solving logical puzzles. Our code and data are available at https://memkklogic.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23123v1-abstract-full').style.display = 'none'; document.getElementById('2410.23123v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22938">arXiv:2410.22938</a> <span> [<a href="https://arxiv.org/pdf/2410.22938">pdf</a>, <a href="https://arxiv.org/format/2410.22938">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <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"> DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hanyang Chen</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yang Jiang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2410.22938v2-abstract-short" style="display: inline;"> The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC wi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22938v2-abstract-full').style.display = 'inline'; document.getElementById('2410.22938v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22938v2-abstract-full" style="display: none;"> The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://github.com/lokol5579/DiffLight-release. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22938v2-abstract-full').style.display = 'none'; document.getElementById('2410.22938v2-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">v1</span> submitted 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by 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/2410.21982">arXiv:2410.21982</a> <span> [<a href="https://arxiv.org/pdf/2410.21982">pdf</a>, <a href="https://arxiv.org/format/2410.21982">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"> A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yuxuan Lin</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+Y">Yang Chang</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+X">Xuan Tong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jiawen Yu</a>, <a href="/search/cs?searchtype=author&query=Liotta%2C+A">Antonio Liotta</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guofan Huang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+W">Wei Song</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+D">Deyu Zeng</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zongze Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yan Wang</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="2410.21982v1-abstract-short" style="display: inline;"> In the advancement of industrial informatization, Unsupervised Industrial Anomaly Detection (UIAD) technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliability of smart manufacturing. While RGB, 3D, and multimodal anomaly detection have demonstrated comprehensive and robust capabilities within the industrial informatization sector, exi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21982v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21982v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21982v1-abstract-full" style="display: none;"> In the advancement of industrial informatization, Unsupervised Industrial Anomaly Detection (UIAD) technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliability of smart manufacturing. While RGB, 3D, and multimodal anomaly detection have demonstrated comprehensive and robust capabilities within the industrial informatization sector, existing reviews on industrial anomaly detection have not sufficiently classified and discussed methods in 3D and multimodal settings. We focus on 3D UIAD and multimodal UIAD, providing a comprehensive summary of unsupervised industrial anomaly detection in three modal settings. Firstly, we compare our surveys with recent works, introducing commonly used datasets, evaluation metrics, and the definitions of anomaly detection problems. Secondly, we summarize five research paradigms in RGB, 3D and multimodal UIAD and three emerging industrial manufacturing optimization directions in RGB UIAD, and review three multimodal feature fusion strategies in multimodal settings. Finally, we outline the primary challenges currently faced by UIAD in three modal settings, and offer insights into future development directions, aiming to provide researchers with a thorough reference and offer new perspectives for the advancement of industrial informatization. Corresponding resources are available at https://github.com/Sunny5250/Awesome-Multi-Setting-UIAD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21982v1-abstract-full').style.display = 'none'; document.getElementById('2410.21982v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, 18 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/2410.21308">arXiv:2410.21308</a> <span> [<a href="https://arxiv.org/pdf/2410.21308">pdf</a>, <a href="https://arxiv.org/format/2410.21308">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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> A Robust Anchor-based Method for Multi-Camera Pedestrian Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wanyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiaqi Zhang</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+D">Dongdong Ge</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yu Lin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Huiwen Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Huikang Liu</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yinyu Ye</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21308v1-abstract-short" style="display: inline;"> This paper addresses the problem of vision-based pedestrian localization, which estimates a pedestrian's location using images and camera parameters. In practice, however, calibrated camera parameters often deviate from the ground truth, leading to inaccuracies in localization. To address this issue, we propose an anchor-based method that leverages fixed-position anchors to reduce the impact of ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21308v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21308v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21308v1-abstract-full" style="display: none;"> This paper addresses the problem of vision-based pedestrian localization, which estimates a pedestrian's location using images and camera parameters. In practice, however, calibrated camera parameters often deviate from the ground truth, leading to inaccuracies in localization. To address this issue, we propose an anchor-based method that leverages fixed-position anchors to reduce the impact of camera parameter errors. We provide a theoretical analysis that demonstrates the robustness of our approach. Experiments conducted on simulated, real-world, and public datasets show that our method significantly improves localization accuracy and remains resilient to noise in camera parameters, compared to methods without anchors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21308v1-abstract-full').style.display = 'none'; document.getElementById('2410.21308v1-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">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/2410.21107">arXiv:2410.21107</a> <span> [<a href="https://arxiv.org/pdf/2410.21107">pdf</a>, <a href="https://arxiv.org/format/2410.21107">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"> Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y+E">Ya-Wei Eileen Lin</a>, <a href="/search/cs?searchtype=author&query=Coifman%2C+R+R">Ronald R. Coifman</a>, <a href="/search/cs?searchtype=author&query=Mishne%2C+G">Gal Mishne</a>, <a href="/search/cs?searchtype=author&query=Talmon%2C+R">Ronen Talmon</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="2410.21107v1-abstract-short" style="display: inline;"> Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimensional data with two key aspects. First, our TWD is specifically designed for data with a latent feature hierarchy, i.e., the features lie in a hierarchical space, in contrast to the usual focus on embedding samples in hyper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21107v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21107v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21107v1-abstract-full" style="display: none;"> Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimensional data with two key aspects. First, our TWD is specifically designed for data with a latent feature hierarchy, i.e., the features lie in a hierarchical space, in contrast to the usual focus on embedding samples in hyperbolic space. Second, while the conventional use of TWD is to speed up the computation of the Wasserstein distance, we use its inherent tree as a means to learn the latent feature hierarchy. The key idea of our method is to embed the features into a multi-scale hyperbolic space using diffusion geometry and then present a new tree decoding method by establishing analogies between the hyperbolic embedding and trees. We show that our TWD computed based on data observations provably recovers the TWD defined with the latent feature hierarchy and that its computation is efficient and scalable. We showcase the usefulness of the proposed TWD in applications to word-document and single-cell RNA-sequencing datasets, demonstrating its advantages over existing TWDs and methods based on pre-trained models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21107v1-abstract-full').style.display = 'none'; document.getElementById('2410.21107v1-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> 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/2410.20769">arXiv:2410.20769</a> <span> [<a href="https://arxiv.org/pdf/2410.20769">pdf</a>, <a href="https://arxiv.org/format/2410.20769">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"> CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiewen Yang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiqun Lin</a>, <a href="/search/cs?searchtype=author&query=Pu%2C+B">Bin Pu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jiarong Guo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiaowei Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaomeng 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="2410.20769v1-abstract-short" style="display: inline;"> Echocardiogram video plays a crucial role in analysing cardiac function and diagnosing cardiac diseases. Current deep neural network methods primarily aim to enhance diagnosis accuracy by incorporating prior knowledge, such as segmenting cardiac structures or lesions annotated by human experts. However, diagnosing the inconsistent behaviours of the heart, which exist across both spatial and tempor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20769v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20769v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20769v1-abstract-full" style="display: none;"> Echocardiogram video plays a crucial role in analysing cardiac function and diagnosing cardiac diseases. Current deep neural network methods primarily aim to enhance diagnosis accuracy by incorporating prior knowledge, such as segmenting cardiac structures or lesions annotated by human experts. However, diagnosing the inconsistent behaviours of the heart, which exist across both spatial and temporal dimensions, remains extremely challenging. For instance, the analysis of cardiac motion acquires both spatial and temporal information from the heartbeat cycle. To address this issue, we propose a novel reconstruction-based approach named CardiacNet to learn a better representation of local cardiac structures and motion abnormalities through echocardiogram videos. CardiacNet is accompanied by the Consistency Deformation Codebook (CDC) and the Consistency Deformed-Discriminator (CDD) to learn the commonalities across abnormal and normal samples by incorporating cardiac prior knowledge. In addition, we propose benchmark datasets named CardiacNet-PAH and CardiacNet-ASD to evaluate the effectiveness of cardiac disease assessment. In experiments, our CardiacNet can achieve state-of-the-art results in three different cardiac disease assessment tasks on public datasets CAMUS, EchoNet, and our datasets. The code and dataset are available at: https://github.com/xmed-lab/CardiacNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20769v1-abstract-full').style.display = 'none'; document.getElementById('2410.20769v1-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> 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">Paper Accepted by ECCV 2024 with Oral Presentation</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20752">arXiv:2410.20752</a> <span> [<a href="https://arxiv.org/pdf/2410.20752">pdf</a>, <a href="https://arxiv.org/format/2410.20752">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"> Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiewen Yang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiqun Lin</a>, <a href="/search/cs?searchtype=author&query=Pu%2C+B">Bin Pu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaomeng 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="2410.20752v1-abstract-short" style="display: inline;"> Quantitative analysis of cardiac motion is crucial for assessing cardiac function. This analysis typically uses imaging modalities such as MRI and Echocardiograms that capture detailed image sequences throughout the heartbeat cycle. Previous methods predominantly focused on the analysis of image pairs lacking consideration of the motion dynamics and spatial variability. Consequently, these methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20752v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20752v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20752v1-abstract-full" style="display: none;"> Quantitative analysis of cardiac motion is crucial for assessing cardiac function. This analysis typically uses imaging modalities such as MRI and Echocardiograms that capture detailed image sequences throughout the heartbeat cycle. Previous methods predominantly focused on the analysis of image pairs lacking consideration of the motion dynamics and spatial variability. Consequently, these methods often overlook the long-term relationships and regional motion characteristic of cardiac. To overcome these limitations, we introduce the \textbf{GPTrack}, a novel unsupervised framework crafted to fully explore the temporal and spatial dynamics of cardiac motion. The GPTrack enhances motion tracking by employing the sequential Gaussian Process in the latent space and encoding statistics by spatial information at each time stamp, which robustly promotes temporal consistency and spatial variability of cardiac dynamics. Also, we innovatively aggregate sequential information in a bidirectional recursive manner, mimicking the behavior of diffeomorphic registration to better capture consistent long-term relationships of motions across cardiac regions such as the ventricles and atria. Our GPTrack significantly improves the precision of motion tracking in both 3D and 4D medical images while maintaining computational efficiency. The code is available at: https://github.com/xmed-lab/GPTrack <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20752v1-abstract-full').style.display = 'none'; document.getElementById('2410.20752v1-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> 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">Paper Accepted by 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/2410.20427">arXiv:2410.20427</a> <span> [<a href="https://arxiv.org/pdf/2410.20427">pdf</a>, <a href="https://arxiv.org/format/2410.20427">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"> YourSkatingCoach: A Figure Skating Video Benchmark for Fine-Grained Element Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei-Yi Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yi-Ling Lin</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Y">Yu-An Su</a>, <a href="/search/cs?searchtype=author&query=Yeh%2C+W">Wei-Hsin Yeh</a>, <a href="/search/cs?searchtype=author&query=Ku%2C+L">Lun-Wei Ku</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="2410.20427v2-abstract-short" style="display: inline;"> Combining sports and machine learning involves leveraging ML algorithms and techniques to extract insight from sports-related data such as player statistics, game footage, and other relevant information. However, datasets related to figure skating in the literature focus primarily on element classification and are currently unavailable or exhibit only limited access, which greatly raise the entry… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20427v2-abstract-full').style.display = 'inline'; document.getElementById('2410.20427v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20427v2-abstract-full" style="display: none;"> Combining sports and machine learning involves leveraging ML algorithms and techniques to extract insight from sports-related data such as player statistics, game footage, and other relevant information. However, datasets related to figure skating in the literature focus primarily on element classification and are currently unavailable or exhibit only limited access, which greatly raise the entry barrier to developing visual sports technology for it. Moreover, when using such data to help athletes improve their skills, we find they are very coarse-grained: they work for learning what an element is, but they are poorly suited to learning whether the element is good or bad. Here we propose air time detection, a novel motion analysis task, the goal of which is to accurately detect the duration of the air time of a jump. We present YourSkatingCoach, a large, novel figure skating dataset which contains 454 videos of jump elements, the detected skater skeletons in each video, along with the gold labels of the start and ending frames of each jump, together as a video benchmark for figure skating. In addition, although this type of task is often viewed as classification, we cast it as a sequential labeling problem and propose a Transformer-based model to calculate the duration. Experimental results show that the proposed model yields a favorable results for a strong baseline. To further verify the generalizability of the fine-grained labels, we apply the same process to other sports as cross-sports tasks but for coarse-grained task action classification. Here we fine-tune the classification to demonstrate that figure skating, as it contains the essential body movements, constitutes a strong foundation for adaptation to other sports. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20427v2-abstract-full').style.display = 'none'; document.getElementById('2410.20427v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 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/2410.20220">arXiv:2410.20220</a> <span> [<a href="https://arxiv.org/pdf/2410.20220">pdf</a>, <a href="https://arxiv.org/format/2410.20220">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> <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"> Neural Fields in Robotics: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Irshad%2C+M+Z">Muhammad Zubair Irshad</a>, <a href="/search/cs?searchtype=author&query=Comi%2C+M">Mauro Comi</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yen-Chen Lin</a>, <a href="/search/cs?searchtype=author&query=Heppert%2C+N">Nick Heppert</a>, <a href="/search/cs?searchtype=author&query=Valada%2C+A">Abhinav Valada</a>, <a href="/search/cs?searchtype=author&query=Ambrus%2C+R">Rares Ambrus</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Tremblay%2C+J">Jonathan Tremblay</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="2410.20220v1-abstract-short" style="display: inline;"> Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D data. Leveraging differentiable rendering, Neural Fields encompass both continuous implicit and explicit neural representations enabling high-fidelity 3D reconstruction, integration of multi-modal sens… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20220v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20220v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20220v1-abstract-full" style="display: none;"> Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D data. Leveraging differentiable rendering, Neural Fields encompass both continuous implicit and explicit neural representations enabling high-fidelity 3D reconstruction, integration of multi-modal sensor data, and generation of novel viewpoints. This survey explores their applications in robotics, emphasizing their potential to enhance perception, planning, and control. Their compactness, memory efficiency, and differentiability, along with seamless integration with foundation and generative models, make them ideal for real-time applications, improving robot adaptability and decision-making. This paper provides a thorough review of Neural Fields in robotics, categorizing applications across various domains and evaluating their strengths and limitations, based on over 200 papers. First, we present four key Neural Fields frameworks: Occupancy Networks, Signed Distance Fields, Neural Radiance Fields, and Gaussian Splatting. Second, we detail Neural Fields' applications in five major robotics domains: pose estimation, manipulation, navigation, physics, and autonomous driving, highlighting key works and discussing takeaways and open challenges. Finally, we outline the current limitations of Neural Fields in robotics and propose promising directions for future research. Project page: https://robonerf.github.io <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20220v1-abstract-full').style.display = 'none'; document.getElementById('2410.20220v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">20 pages, 20 figures. Project Page: https://robonerf.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/2410.19848">arXiv:2410.19848</a> <span> [<a href="https://arxiv.org/pdf/2410.19848">pdf</a>, <a href="https://arxiv.org/format/2410.19848">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"> Benchmarking Large Language Models for Image Classification of Marine Mammals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qi%2C+Y">Yijiashun Qi</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+S">Shuzhang Cai</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zunduo Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaming Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yanbin Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhiqiang 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="2410.19848v1-abstract-short" style="display: inline;"> As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on mari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19848v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19848v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19848v1-abstract-full" style="display: none;"> As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on marine mammals, which are indispensable for ecological equilibrium. In this work, we build a benchmark dataset with 1,423 images of 65 kinds of marine mammals, where each animal is uniquely classified into different levels of class, ranging from species-level to medium-level to group-level. Moreover, we evaluate several approaches for classifying these marine mammals: (1) machine learning (ML) algorithms using embeddings provided by neural networks, (2) influential pre-trained neural networks, (3) zero-shot models: CLIP and LLMs, and (4) a novel LLM-based multi-agent system (MAS). The results demonstrate the strengths of traditional models and LLMs in different aspects, and the MAS can further improve the classification performance. The dataset is available on GitHub: https://github.com/yeyimilk/LLM-Vision-Marine-Animals.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19848v1-abstract-full').style.display = 'none'; document.getElementById('2410.19848v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICKG 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19320">arXiv:2410.19320</a> <span> [<a href="https://arxiv.org/pdf/2410.19320">pdf</a>, <a href="https://arxiv.org/ps/2410.19320">ps</a>, <a href="https://arxiv.org/format/2410.19320">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Pseudorandomness in the (Inverseless) Haar Random Oracle Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ananth%2C+P">Prabhanjan Ananth</a>, <a href="/search/cs?searchtype=author&query=Bostanci%2C+J">John Bostanci</a>, <a href="/search/cs?searchtype=author&query=Gulati%2C+A">Aditya Gulati</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yao-Ting Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19320v1-abstract-short" style="display: inline;"> We study the (in)feasibility of quantum pseudorandom notions in a quantum analog of the random oracle model, where all the parties, including the adversary, have oracle access to the same Haar random unitary. In this model, we show the following: - (Unbounded-query secure) pseudorandom unitaries (PRU) exist. Moreover, the PRU construction makes two calls to the Haar oracle. - We consider const… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19320v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19320v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19320v1-abstract-full" style="display: none;"> We study the (in)feasibility of quantum pseudorandom notions in a quantum analog of the random oracle model, where all the parties, including the adversary, have oracle access to the same Haar random unitary. In this model, we show the following: - (Unbounded-query secure) pseudorandom unitaries (PRU) exist. Moreover, the PRU construction makes two calls to the Haar oracle. - We consider constructions of PRUs making a single call to the Haar oracle. In this setting, we show that unbounded-query security is impossible to achieve. We complement this result by showing that bounded-query secure PRUs do exist with a single query to the Haar oracle. - We show that multi-copy pseudorandom state generators and function-like state generators (with classical query access), making a single call to the Haar oracle, exist. Our results have two consequences: (a) when the Haar random unitary is instantiated suitably, our results present viable approaches for building quantum pseudorandom objects without relying upon one-way functions and, (b) for the first time, we show that the key length in pseudorandom unitaries can be generically shrunk (relative to the output length). Our results are also some of the first usecases of the new "path recording" formalism for Haar random unitaries, introduced in the recent breakthrough work of Ma and Huang. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19320v1-abstract-full').style.display = 'none'; document.getElementById('2410.19320v1-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">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">51 pages; 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17526">arXiv:2410.17526</a> <span> [<a href="https://arxiv.org/pdf/2410.17526">pdf</a>, <a href="https://arxiv.org/format/2410.17526">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"> GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+Z">Zhixia He</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Chen Zhao</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+M">Minglai Shao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yujie Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Dong Li</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Q">Qin Tian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17526v1-abstract-short" style="display: inline;"> Out-of-distribution (OOD) detection poses a significant challenge for Graph Neural Networks (GNNs), particularly in open-world scenarios with varying distribution shifts. Most existing OOD detection methods on graphs primarily focus on identifying instances in test data domains caused by either semantic shifts (changes in data classes) or covariate shifts (changes in data features), while leaving… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17526v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17526v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17526v1-abstract-full" style="display: none;"> Out-of-distribution (OOD) detection poses a significant challenge for Graph Neural Networks (GNNs), particularly in open-world scenarios with varying distribution shifts. Most existing OOD detection methods on graphs primarily focus on identifying instances in test data domains caused by either semantic shifts (changes in data classes) or covariate shifts (changes in data features), while leaving the simultaneous occurrence of both distribution shifts under-explored. In this work, we address both types of shifts simultaneously and introduce a novel challenge for OOD detection on graphs: graph-level semantic OOD detection under covariate shift. In this scenario, variations between the training and test domains result from the concurrent presence of both covariate and semantic shifts, where only graphs associated with unknown classes are identified as OOD samples (OODs). To tackle this challenge, we propose a novel two-phase framework called Graph Disentangled Diffusion Augmentation (GDDA). The first phase focuses on disentangling graph representations into domain-invariant semantic factors and domain-specific style factors. In the second phase, we introduce a novel distribution-shift-controlled score-based generative diffusion model that generates latent factors outside the training semantic and style spaces. Additionally, auxiliary pseudo-in-distribution (InD) and pseudo-OOD graph representations are employed to enhance the effectiveness of the energy-based semantic OOD detector. Extensive empirical studies on three benchmark datasets demonstrate that our approach outperforms state-of-the-art baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17526v1-abstract-full').style.display = 'none'; document.getElementById('2410.17526v1-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">4 pages, 6 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/2410.17238">arXiv:2410.17238</a> <span> [<a href="https://arxiv.org/pdf/2410.17238">pdf</a>, <a href="https://arxiv.org/format/2410.17238">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chi%2C+Y">Yizhou Chi</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yizhang Lin</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+S">Sirui Hong</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+D">Duyi Pan</a>, <a href="/search/cs?searchtype=author&query=Fei%2C+Y">Yaying Fei</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+G">Guanghao Mei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bangbang Liu</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+T">Tianqi Pang</a>, <a href="/search/cs?searchtype=author&query=Kwok%2C+J">Jacky Kwok</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Ceyao Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bang Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chenglin 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="2410.17238v1-abstract-short" style="display: inline;"> Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents have shown promise in automating machine learning tasks, they often generate low-diversity and suboptimal code, even after multiple iterations. To overcome these… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17238v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17238v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17238v1-abstract-full" style="display: none;"> Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents have shown promise in automating machine learning tasks, they often generate low-diversity and suboptimal code, even after multiple iterations. To overcome these limitations, we introduce Tree-Search Enhanced LLM Agents (SELA), an innovative agent-based system that leverages Monte Carlo Tree Search (MCTS) to optimize the AutoML process. By representing pipeline configurations as trees, our framework enables agents to conduct experiments intelligently and iteratively refine their strategies, facilitating a more effective exploration of the machine learning solution space. This novel approach allows SELA to discover optimal pathways based on experimental feedback, improving the overall quality of the solutions. In an extensive evaluation across 20 machine learning datasets, we compare the performance of traditional and agent-based AutoML methods, demonstrating that SELA achieves a win rate of 65% to 80% against each baseline across all datasets. These results underscore the significant potential of agent-based strategies in AutoML, offering a fresh perspective on tackling complex machine learning challenges. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17238v1-abstract-full').style.display = 'none'; document.getElementById('2410.17238v1-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">The code is available at https://github.com/geekan/MetaGPT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17136">arXiv:2410.17136</a> <span> [<a href="https://arxiv.org/pdf/2410.17136">pdf</a>, <a href="https://arxiv.org/format/2410.17136">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"> AlphaChimp: Tracking and Behavior Recognition of Chimpanzees </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xiaoxuan Ma</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yutang Lin</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yuan Xu</a>, <a href="/search/cs?searchtype=author&query=Kaufhold%2C+S+P">Stephan P. Kaufhold</a>, <a href="/search/cs?searchtype=author&query=Terwilliger%2C+J">Jack Terwilliger</a>, <a href="/search/cs?searchtype=author&query=Meza%2C+A">Andres Meza</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yixin Zhu</a>, <a href="/search/cs?searchtype=author&query=Rossano%2C+F">Federico Rossano</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yizhou 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="2410.17136v2-abstract-short" style="display: inline;"> Understanding non-human primate behavior is crucial for improving animal welfare, modeling social behavior, and gaining insights into both distinctly human and shared behaviors. Despite recent advances in computer vision, automated analysis of primate behavior remains challenging due to the complexity of their social interactions and the lack of specialized algorithms. Existing methods often strug… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17136v2-abstract-full').style.display = 'inline'; document.getElementById('2410.17136v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17136v2-abstract-full" style="display: none;"> Understanding non-human primate behavior is crucial for improving animal welfare, modeling social behavior, and gaining insights into both distinctly human and shared behaviors. Despite recent advances in computer vision, automated analysis of primate behavior remains challenging due to the complexity of their social interactions and the lack of specialized algorithms. Existing methods often struggle with the nuanced behaviors and frequent occlusions characteristic of primate social dynamics. This study aims to develop an effective method for automated detection, tracking, and recognition of chimpanzee behaviors in video footage. Here we show that our proposed method, AlphaChimp, an end-to-end approach that simultaneously detects chimpanzee positions and estimates behavior categories from videos, significantly outperforms existing methods in behavior recognition. AlphaChimp achieves approximately 10% higher tracking accuracy and a 20% improvement in behavior recognition compared to state-of-the-art methods, particularly excelling in the recognition of social behaviors. This superior performance stems from AlphaChimp's innovative architecture, which integrates temporal feature fusion with a Transformer-based self-attention mechanism, enabling more effective capture and interpretation of complex social interactions among chimpanzees. Our approach bridges the gap between computer vision and primatology, enhancing technical capabilities and deepening our understanding of primate communication and sociality. We release our code and models and hope this will facilitate future research in animal social dynamics. This work contributes to ethology, cognitive science, and artificial intelligence, offering new perspectives on social intelligence. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17136v2-abstract-full').style.display = 'none'; document.getElementById('2410.17136v2-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">v1</span> submitted 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">An extension of ChimpACT [arXiv:2310.16447], proposes AlphaChimp for tracking and behavior recognition of chimpanzees. arXiv admin note: substantial text overlap with arXiv:2310.16447</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16571">arXiv:2410.16571</a> <span> [<a href="https://arxiv.org/pdf/2410.16571">pdf</a>, <a href="https://arxiv.org/format/2410.16571">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> <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"> Implicit Contact Diffuser: Sequential Contact Reasoning with Latent Point Cloud Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zixuan Huang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yinong He</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yating Lin</a>, <a href="/search/cs?searchtype=author&query=Berenson%2C+D">Dmitry Berenson</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="2410.16571v1-abstract-short" style="display: inline;"> Long-horizon contact-rich manipulation has long been a challenging problem, as it requires reasoning over both discrete contact modes and continuous object motion. We introduce Implicit Contact Diffuser (ICD), a diffusion-based model that generates a sequence of neural descriptors that specify a series of contact relationships between the object and the environment. This sequence is then used as g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16571v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16571v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16571v1-abstract-full" style="display: none;"> Long-horizon contact-rich manipulation has long been a challenging problem, as it requires reasoning over both discrete contact modes and continuous object motion. We introduce Implicit Contact Diffuser (ICD), a diffusion-based model that generates a sequence of neural descriptors that specify a series of contact relationships between the object and the environment. This sequence is then used as guidance for an MPC method to accomplish a given task. The key advantage of this approach is that the latent descriptors provide more task-relevant guidance to MPC, helping to avoid local minima for contact-rich manipulation tasks. Our experiments demonstrate that ICD outperforms baselines on complex, long-horizon, contact-rich manipulation tasks, such as cable routing and notebook folding. Additionally, our experiments also indicate that \methodshort can generalize a target contact relationship to a different environment. More visualizations can be found on our website $\href{https://implicit-contact-diffuser.github.io/}{https://implicit-contact-diffuser.github.io}$ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16571v1-abstract-full').style.display = 'none'; document.getElementById('2410.16571v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In submussion</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15297">arXiv:2410.15297</a> <span> [<a href="https://arxiv.org/pdf/2410.15297">pdf</a>, <a href="https://arxiv.org/format/2410.15297">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"> Redefining Proactivity for Information Seeking Dialogue </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+J+Y">Jing Yang Lee</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Seokhwan Kim</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+K">Kartik Mehta</a>, <a href="/search/cs?searchtype=author&query=Kao%2C+J">Jiun-Yu Kao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yu-Hsiang Lin</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+A">Arpit Gupta</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="2410.15297v2-abstract-short" style="display: inline;"> Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15297v2-abstract-full').style.display = 'inline'; document.getElementById('2410.15297v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15297v2-abstract-full" style="display: none;"> Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response `proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15297v2-abstract-full').style.display = 'none'; document.getElementById('2410.15297v2-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">v1</span> submitted 20 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/2410.14641">arXiv:2410.14641</a> <span> [<a href="https://arxiv.org/pdf/2410.14641">pdf</a>, <a href="https://arxiv.org/format/2410.14641">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"> Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tian%2C+R">Runchu Tian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanghao Li</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yuepeng Fu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+S">Siyang Deng</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Q">Qinyu Luo</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+C">Cheng Qian</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuo Wang</a>, <a href="/search/cs?searchtype=author&query=Cong%2C+X">Xin Cong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhong Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yesai Wu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yankai Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Huadong Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaojiang Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.14641v1-abstract-short" style="display: inline;"> Positional bias in large language models (LLMs) hinders their ability to effectively process long inputs. A prominent example is the "lost in the middle" phenomenon, where LLMs struggle to utilize relevant information situated in the middle of the input. While prior research primarily focuses on single pieces of relevant information, real-world applications often involve multiple relevant informat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14641v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14641v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14641v1-abstract-full" style="display: none;"> Positional bias in large language models (LLMs) hinders their ability to effectively process long inputs. A prominent example is the "lost in the middle" phenomenon, where LLMs struggle to utilize relevant information situated in the middle of the input. While prior research primarily focuses on single pieces of relevant information, real-world applications often involve multiple relevant information pieces. To bridge this gap, we present LongPiBench, a benchmark designed to assess positional bias involving multiple pieces of relevant information. Thorough experiments are conducted with five commercial and six open-source models. These experiments reveal that while most current models are robust against the "lost in the middle" issue, there exist significant biases related to the spacing of relevant information pieces. These findings highlight the importance of evaluating and reducing positional biases to advance LLM's capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14641v1-abstract-full').style.display = 'none'; document.getElementById('2410.14641v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">work in progress</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=Lin%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Lin%2C+Y&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