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 1,016 results for author: <span class="mathjax">Zhang, G</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=Zhang%2C+G">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="Zhang, G"> </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=Zhang%2C+G&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="Zhang, G"> <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=Zhang%2C+G&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&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/2411.13560">arXiv:2411.13560</a> <span> [<a href="https://arxiv.org/pdf/2411.13560">pdf</a>, <a href="https://arxiv.org/format/2411.13560">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="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yichen Shi</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhuofu Tao</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yuhao Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+T">Tianjia Zhou</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Cheng Chang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yaxing Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+B">Bingyu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Genhao Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Alvin Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiping Yu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Ting-Jung Lin</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Lei He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13560v1-abstract-short" style="display: inline;"> High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13560v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13560v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13560v1-abstract-full" style="display: none;"> High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements in the automatic design process for large-scale AMS circuits. However, the absence of high-quality datasets has led to issues such as model hallucination, which undermines the robustness of automatically generated circuit designs. To address this issue, this paper introduces AMSnet-KG, a dataset encompassing various AMS circuit schematics and netlists. We construct a knowledge graph with annotations on detailed functional and performance characteristics. Facilitated by AMSnet-KG, we propose an automated AMS circuit generation framework that utilizes the comprehensive knowledge embedded in LLMs. We first formulate a design strategy (e.g., circuit architecture using a number of circuit components) based on required specifications. Next, matched circuit components are retrieved and assembled into a complete topology, and transistor sizing is obtained through Bayesian optimization. Simulation results of the netlist are fed back to the LLM for further topology refinement, ensuring the circuit design specifications are met. We perform case studies of operational amplifier and comparator design to verify the automatic design flow from specifications to netlists with minimal human effort. The dataset used in this paper will be open-sourced upon publishing of this paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13560v1-abstract-full').style.display = 'none'; document.getElementById('2411.13560v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">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/2411.13291">arXiv:2411.13291</a> <span> [<a href="https://arxiv.org/pdf/2411.13291">pdf</a>, <a href="https://arxiv.org/format/2411.13291">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"> DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+W">Weicai Ye</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhan%2C+R">Ruohao Zhan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+D">Di Huang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xiaoshui Huang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Haoyi Zhu</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+H">Hujun Bao</a>, <a href="/search/cs?searchtype=author&query=Ouyang%2C+W">Wanli Ouyang</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tong He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13291v1-abstract-short" style="display: inline;"> This paper proposes a concise, elegant, and robust pipeline to estimate smooth camera trajectories and obtain dense point clouds for casual videos in the wild. Traditional frameworks, such as ParticleSfM~\cite{zhao2022particlesfm}, address this problem by sequentially computing the optical flow between adjacent frames to obtain point trajectories. They then remove dynamic trajectories through moti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13291v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13291v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13291v1-abstract-full" style="display: none;"> This paper proposes a concise, elegant, and robust pipeline to estimate smooth camera trajectories and obtain dense point clouds for casual videos in the wild. Traditional frameworks, such as ParticleSfM~\cite{zhao2022particlesfm}, address this problem by sequentially computing the optical flow between adjacent frames to obtain point trajectories. They then remove dynamic trajectories through motion segmentation and perform global bundle adjustment. However, the process of estimating optical flow between two adjacent frames and chaining the matches can introduce cumulative errors. Additionally, motion segmentation combined with single-view depth estimation often faces challenges related to scale ambiguity. To tackle these challenges, we propose a dynamic-aware tracking any point (DATAP) method that leverages consistent video depth and point tracking. Specifically, our DATAP addresses these issues by estimating dense point tracking across the video sequence and predicting the visibility and dynamics of each point. By incorporating the consistent video depth prior, the performance of motion segmentation is enhanced. With the integration of DATAP, it becomes possible to estimate and optimize all camera poses simultaneously by performing global bundle adjustments for point tracking classified as static and visible, rather than relying on incremental camera registration. Extensive experiments on dynamic sequences, e.g., Sintel and TUM RGBD dynamic sequences, and on the wild video, e.g., DAVIS, demonstrate that the proposed method achieves state-of-the-art performance in terms of camera pose estimation even in complex dynamic challenge scenes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13291v1-abstract-full').style.display = 'none'; document.getElementById('2411.13291v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10714">arXiv:2411.10714</a> <span> [<a href="https://arxiv.org/pdf/2411.10714">pdf</a>, <a href="https://arxiv.org/format/2411.10714">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> FlexFL: Flexible and Effective Fault Localization with Open-Source Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chuyang Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhongxin Liu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiaoxue Ren</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gehao Zhang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+M">Ming Liang</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+D">David Lo</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="2411.10714v1-abstract-short" style="display: inline;"> Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are limited in flexibility. They rely on bug-triggering test cases to perform FL and cannot make use of other available bug-related information, e.g., bug reports. Sec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10714v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10714v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10714v1-abstract-full" style="display: none;"> Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are limited in flexibility. They rely on bug-triggering test cases to perform FL and cannot make use of other available bug-related information, e.g., bug reports. Second, they are built upon proprietary LLMs, which are, although powerful, confronted with risks in data privacy. To address these limitations, we propose a novel LLM-based FL framework named FlexFL, which can flexibly leverage different types of bug-related information and effectively work with open-source LLMs. FlexFL is composed of two stages. In the first stage, FlexFL reduces the search space of buggy code using state-of-the-art FL techniques of different families and provides a candidate list of bug-related methods. In the second stage, FlexFL leverages LLMs to delve deeper to double-check the code snippets of methods suggested by the first stage and refine fault localization results. In each stage, FlexFL constructs agents based on open-source LLMs, which share the same pipeline that does not postulate any type of bug-related information and can interact with function calls without the out-of-the-box capability. Extensive experimental results on Defects4J demonstrate that FlexFL outperforms the baselines and can work with different open-source LLMs. Specifically, FlexFL with a lightweight open-source LLM Llama3-8B can locate 42 and 63 more bugs than two state-of-the-art LLM-based FL approaches AutoFL and AgentFL that both use GPT-3.5. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10714v1-abstract-full').style.display = 'none'; document.getElementById('2411.10714v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 3 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/2411.08586">arXiv:2411.08586</a> <span> [<a href="https://arxiv.org/pdf/2411.08586">pdf</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"> Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension:Testing and Evaluation of the NBCE Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Fukuyama%2C+K">Keita Fukuyama</a>, <a href="/search/cs?searchtype=author&query=Kishimoto%2C+K">Kazumasa Kishimoto</a>, <a href="/search/cs?searchtype=author&query=Kuroda%2C+T">Tomohiro Kuroda</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="2411.08586v2-abstract-short" style="display: inline;"> Summarizing patient clinical notes is vital for reducing documentation burdens. Current manual summarization makes medical staff struggle. We propose an automatic method using LLMs, but long inputs cause LLMs to lose context, reducing output quality especially in small size model. We used a 7B model, open-calm-7b, enhanced with Native Bayes Context Extend and a redesigned decoding mechanism to ref… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08586v2-abstract-full').style.display = 'inline'; document.getElementById('2411.08586v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08586v2-abstract-full" style="display: none;"> Summarizing patient clinical notes is vital for reducing documentation burdens. Current manual summarization makes medical staff struggle. We propose an automatic method using LLMs, but long inputs cause LLMs to lose context, reducing output quality especially in small size model. We used a 7B model, open-calm-7b, enhanced with Native Bayes Context Extend and a redesigned decoding mechanism to reference one sentence at a time, keeping inputs within context windows, 2048 tokens. Our improved model achieved near parity with Google's over 175B Gemini on ROUGE-L metrics with 200 samples, indicating strong performance using less resources, enhancing automated EMR summarization feasibility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08586v2-abstract-full').style.display = 'none'; document.getElementById('2411.08586v2-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">v1</span> submitted 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/2411.08510">arXiv:2411.08510</a> <span> [<a href="https://arxiv.org/pdf/2411.08510">pdf</a>, <a href="https://arxiv.org/format/2411.08510">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiu%2C+R">Ruidi Qiu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G+L">Grace Li Zhang</a>, <a href="/search/cs?searchtype=author&query=Drechsler%2C+R">Rolf Drechsler</a>, <a href="/search/cs?searchtype=author&query=Schlichtmann%2C+U">Ulf Schlichtmann</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bing 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="2411.08510v1-abstract-short" style="display: inline;"> Functional simulation is an essential step in digital hardware design. Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for hardware testbench generation tasks. However, the inherent instability associated with LLMs often leads to functional errors in the generated testbenches. Previous methods do not incorporate automatic functional correction mechanisms with… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08510v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08510v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08510v1-abstract-full" style="display: none;"> Functional simulation is an essential step in digital hardware design. Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for hardware testbench generation tasks. However, the inherent instability associated with LLMs often leads to functional errors in the generated testbenches. Previous methods do not incorporate automatic functional correction mechanisms without human intervention and still suffer from low success rates, especially for sequential tasks. To address this issue, we propose CorrectBench, an automatic testbench generation framework with functional self-validation and self-correction. Utilizing only the RTL specification in natural language, the proposed approach can validate the correctness of the generated testbenches with a success rate of 88.85%. Furthermore, the proposed LLM-based corrector employs bug information obtained during the self-validation process to perform functional self-correction on the generated testbenches. The comparative analysis demonstrates that our method achieves a pass ratio of 70.13% across all evaluated tasks, compared with the previous LLM-based testbench generation framework's 52.18% and a direct LLM-based generation method's 33.33%. Specifically in sequential circuits, our work's performance is 62.18% higher than previous work in sequential tasks and almost 5 times the pass ratio of the direct method. The codes and experimental results are open-sourced at the link: https://github.com/AutoBench/CorrectBench <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08510v1-abstract-full').style.display = 'none'; document.getElementById('2411.08510v1-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/2411.07199">arXiv:2411.07199</a> <span> [<a href="https://arxiv.org/pdf/2411.07199">pdf</a>, <a href="https://arxiv.org/format/2411.07199">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"> OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wei%2C+C">Cong Wei</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Z">Zheyang Xiong</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+W">Weiming Ren</a>, <a href="/search/cs?searchtype=author&query=Du%2C+X">Xinrun Du</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wenhu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07199v1-abstract-short" style="display: inline;"> Instruction-guided image editing methods have demonstrated significant potential by training diffusion models on automatically synthesized or manually annotated image editing pairs. However, these methods remain far from practical, real-life applications. We identify three primary challenges contributing to this gap. Firstly, existing models have limited editing skills due to the biased synthesis… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07199v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07199v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07199v1-abstract-full" style="display: none;"> Instruction-guided image editing methods have demonstrated significant potential by training diffusion models on automatically synthesized or manually annotated image editing pairs. However, these methods remain far from practical, real-life applications. We identify three primary challenges contributing to this gap. Firstly, existing models have limited editing skills due to the biased synthesis process. Secondly, these methods are trained with datasets with a high volume of noise and artifacts. This is due to the application of simple filtering methods like CLIP-score. Thirdly, all these datasets are restricted to a single low resolution and fixed aspect ratio, limiting the versatility to handle real-world use cases. In this paper, we present \omniedit, which is an omnipotent editor to handle seven different image editing tasks with any aspect ratio seamlessly. Our contribution is in four folds: (1) \omniedit is trained by utilizing the supervision from seven different specialist models to ensure task coverage. (2) we utilize importance sampling based on the scores provided by large multimodal models (like GPT-4o) instead of CLIP-score to improve the data quality. (3) we propose a new editing architecture called EditNet to greatly boost the editing success rate, (4) we provide images with different aspect ratios to ensure that our model can handle any image in the wild. We have curated a test set containing images of different aspect ratios, accompanied by diverse instructions to cover different tasks. Both automatic evaluation and human evaluations demonstrate that \omniedit can significantly outperform all the existing models. Our code, dataset and model will be available at \url{https://tiger-ai-lab.github.io/OmniEdit/} <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07199v1-abstract-full').style.display = 'none'; document.getElementById('2411.07199v1-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">21 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04905">arXiv:2411.04905</a> <span> [<a href="https://arxiv.org/pdf/2411.04905">pdf</a>, <a href="https://arxiv.org/format/2411.04905">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="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+S">Siming Huang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+T">Tianhao Cheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+K">J. K. Liu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+J">Jiaran Hao</a>, <a href="/search/cs?searchtype=author&query=Song%2C+L">Liuyihan Song</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yang Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">J. Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+H">J. H. Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+L">Linzheng Chai</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+R">Ruifeng Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+J">Jie Fu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zili Wang</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+Y">Yuan Qi</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yinghui Xu</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+W">Wei Chu</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="2411.04905v2-abstract-short" style="display: inline;"> Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04905v2-abstract-full').style.display = 'inline'; document.getElementById('2411.04905v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04905v2-abstract-full" style="display: none;"> Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent training protocols, remain limited. The scarcity is due to various challenges, including resource constraints, ethical considerations, and the competitive advantages of keeping models advanced. To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community. Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental ablation results, and detailed training protocols for open scientific research. Through this comprehensive release, we identify the key ingredients for building a top-tier code LLM: (1) code optimized heuristic rules for data cleaning and methods for data deduplication, (2) recall of text corpus related to code and (3) high-quality synthetic data in both annealing and supervised fine-tuning stages. By offering this level of openness, we aim to broaden access to all aspects of a top-tier code LLM, with OpenCoder serving as both a powerful model and an open foundation to accelerate research, and enable reproducible advancements in code AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04905v2-abstract-full').style.display = 'none'; document.getElementById('2411.04905v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02785">arXiv:2411.02785</a> <span> [<a href="https://arxiv.org/pdf/2411.02785">pdf</a>, <a href="https://arxiv.org/format/2411.02785">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"> Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vega%2C+J">Jason Vega</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Junsheng Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gaokai Zhang</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+H">Hangoo Kang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Minjia Zhang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+G">Gagandeep Singh</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="2411.02785v1-abstract-short" style="display: inline;"> Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking methods, such as adversarial attacks. However, these jailbreak methods can be rather costly or involve a non-trivial amount of creativity and effort, introducing th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02785v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02785v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02785v1-abstract-full" style="display: none;"> Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking methods, such as adversarial attacks. However, these jailbreak methods can be rather costly or involve a non-trivial amount of creativity and effort, introducing the assumption that malicious users are high-resource or sophisticated. In this paper, we study how simple random augmentations to the input prompt affect safety alignment effectiveness in state-of-the-art LLMs, such as Llama 3 and Qwen 2. We perform an in-depth evaluation of 17 different models and investigate the intersection of safety under random augmentations with multiple dimensions: augmentation type, model size, quantization, fine-tuning-based defenses, and decoding strategies (e.g., sampling temperature). We show that low-resource and unsophisticated attackers, i.e. $\textit{stochastic monkeys}$, can significantly improve their chances of bypassing alignment with just 25 random augmentations per prompt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02785v1-abstract-full').style.display = 'none'; document.getElementById('2411.02785v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under peer review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02310">arXiv:2411.02310</a> <span> [<a href="https://arxiv.org/pdf/2411.02310">pdf</a>, <a href="https://arxiv.org/format/2411.02310">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"> MdEval: Massively Multilingual Code Debugging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shukai Liu</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+L">Linzheng Chai</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jiajun Shi</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">He Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liran Wang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+K">Ke Jin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Hualei Zhu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shuyue Guo</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tao Sun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+Y">Yunlong Duan</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yu Hao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Liqun Yang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+G">Guanglin Niu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhoujun 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="2411.02310v1-abstract-short" style="display: inline;"> Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet. Programming benchmarks, typically consisting of buggy code snippet and their associated test cases, are used to assess the debugging capabilities of LLMs. However, many existing benchmarks primarily focus on Python and are often limited in term… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02310v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02310v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02310v1-abstract-full" style="display: none;"> Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet. Programming benchmarks, typically consisting of buggy code snippet and their associated test cases, are used to assess the debugging capabilities of LLMs. However, many existing benchmarks primarily focus on Python and are often limited in terms of language diversity (e.g., DebugBench and DebugEval). To advance the field of multilingual debugging with LLMs, we propose the first massively multilingual debugging benchmark, which includes 3.6K test samples of 18 programming languages and covers the automated program repair (APR) task, the code review (CR) task, and the bug identification (BI) task. Further, we introduce the debugging instruction corpora MDEVAL-INSTRUCT by injecting bugs into the correct multilingual queries and solutions (xDebugGen). Further, a multilingual debugger xDebugCoder trained on MDEVAL-INSTRUCT as a strong baseline specifically to handle the bugs of a wide range of programming languages (e.g. "Missing Mut" in language Rust and "Misused Macro Definition" in language C). Our extensive experiments on MDEVAL reveal a notable performance gap between open-source models and closed-source LLMs (e.g., GPT and Claude series), highlighting huge room for improvement in multilingual code debugging scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02310v1-abstract-full').style.display = 'none'; document.getElementById('2411.02310v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02183">arXiv:2411.02183</a> <span> [<a href="https://arxiv.org/pdf/2411.02183">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Vehicles, Pedestrians, and E-bikes: a Three-party Game at Right-turn-on-red Crossroads Revealing the Dual and Irrational Role of E-bikes that Risks Traffic Safety </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gangcheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+Y">Yeshuo Shu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Keyi Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuxuan Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Donghang Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Liyan Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02183v1-abstract-short" style="display: inline;"> The widespread use of e-bikes has facilitated short-distance travel yet led to confusion and safety problems in road traffic. This study focuses on the dual characteristics of e-bikes in traffic conflicts: they resemble pedestrians when interacting with motor vehicles and behave like motor vehicles when in conflict with pedestrians, which raises the right of way concerns when potential conflicts a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02183v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02183v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02183v1-abstract-full" style="display: none;"> The widespread use of e-bikes has facilitated short-distance travel yet led to confusion and safety problems in road traffic. This study focuses on the dual characteristics of e-bikes in traffic conflicts: they resemble pedestrians when interacting with motor vehicles and behave like motor vehicles when in conflict with pedestrians, which raises the right of way concerns when potential conflicts are at stake. Using the Quantal Response Equilibrium model, this research analyzes the behavioral choice differences of three groups of road users (vehicle-pedestrian, vehicle-e-bike, e-bike-pedestrian) at right-turn-on-red crossroads in right-turning lines and straight-going lines conflict scenarios. The results show that the behavior of e-bikes is more similar to that of motor vehicles than pedestrians overall, and their interactions with either pedestrians or motor vehicles do not establish a reasonable order, increasing the likelihood of confusion and conflict. In contrast, a mutual understanding has developed between motor vehicles and pedestrians, where motor vehicles tend to yield, and pedestrians tend to cross. By clarifying the game theoretical model and introducing the rationality parameter, this study precisely locates the role of e-bikes among road users, which provides a reliable theoretical basis for optimizing traffic regulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02183v1-abstract-full').style.display = 'none'; document.getElementById('2411.02183v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 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/2411.02059">arXiv:2411.02059</a> <span> [<a href="https://arxiv.org/pdf/2411.02059">pdf</a>, <a href="https://arxiv.org/format/2411.02059">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="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> TableGPT2: A Large Multimodal Model with Tabular Data Integration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Su%2C+A">Aofeng Su</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+A">Aowen Wang</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+C">Chao Ye</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+C">Chen Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ga Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">Gang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+G">Guangcheng Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haobo Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Haokai Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hao Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoze Li</a>, <a href="/search/cs?searchtype=author&query=Lan%2C+H">Haoxuan Lan</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+J">Jiaming Tian</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+J">Jing Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Junbo Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Junlin Zhou</a>, <a href="/search/cs?searchtype=author&query=Shou%2C+K">Kaizhe Shou</a>, <a href="/search/cs?searchtype=author&query=Zha%2C+L">Liangyu Zha</a>, <a href="/search/cs?searchtype=author&query=Long%2C+L">Lin Long</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Liyao Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+P">Pengzuo Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Q">Qingyi Huang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Saisai Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tao Zhang</a> , et al. (8 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="2411.02059v3-abstract-short" style="display: inline;"> The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains. This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02059v3-abstract-full').style.display = 'inline'; document.getElementById('2411.02059v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02059v3-abstract-full" style="display: none;"> The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains. This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise solutions that many current LLMs may struggle to provide. In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593.8K tables and 2.36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research. This extensive training enables TableGPT2 to excel in table-centric tasks while maintaining strong general language and coding abilities. One of TableGPT2's key innovations is its novel table encoder, specifically designed to capture schema-level and cell-level information. This encoder strengthens the model's ability to handle ambiguous queries, missing column names, and irregular tables commonly encountered in real-world applications. Similar to visual language models, this pioneering approach integrates with the decoder to form a robust large multimodal model. We believe the results are compelling: over 23 benchmarking metrics, TableGPT2 achieves an average performance improvement of 35.20% in the 7B model and 49.32% in the 72B model over prior benchmark-neutral LLMs, with robust general-purpose capabilities intact. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02059v3-abstract-full').style.display = 'none'; document.getElementById('2411.02059v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01893">arXiv:2411.01893</a> <span> [<a href="https://arxiv.org/pdf/2411.01893">pdf</a>, <a href="https://arxiv.org/format/2411.01893">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 Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yitong Dong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yijin Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhaoyang Huang</a>, <a href="/search/cs?searchtype=author&query=Bian%2C+W">Weikang Bian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jingbo Liu</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+H">Hujun Bao</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Z">Zhaopeng Cui</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongsheng Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01893v1-abstract-short" style="display: inline;"> In this paper, we propose a novel multi-view stereo (MVS) framework that gets rid of the depth range prior. Unlike recent prior-free MVS methods that work in a pair-wise manner, our method simultaneously considers all the source images. Specifically, we introduce a Multi-view Disparity Attention (MDA) module to aggregate long-range context information within and across multi-view images. Consideri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01893v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01893v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01893v1-abstract-full" style="display: none;"> In this paper, we propose a novel multi-view stereo (MVS) framework that gets rid of the depth range prior. Unlike recent prior-free MVS methods that work in a pair-wise manner, our method simultaneously considers all the source images. Specifically, we introduce a Multi-view Disparity Attention (MDA) module to aggregate long-range context information within and across multi-view images. Considering the asymmetry of the epipolar disparity flow, the key to our method lies in accurately modeling multi-view geometric constraints. We integrate pose embedding to encapsulate information such as multi-view camera poses, providing implicit geometric constraints for multi-view disparity feature fusion dominated by attention. Additionally, we construct corresponding hidden states for each source image due to significant differences in the observation quality of the same pixel in the reference frame across multiple source frames. We explicitly estimate the quality of the current pixel corresponding to sampled points on the epipolar line of the source image and dynamically update hidden states through the uncertainty estimation module. Extensive results on the DTU dataset and Tanks&Temple benchmark demonstrate the effectiveness of our method. The code is available at our project page: https://zju3dv.github.io/GD-PoseMVS/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01893v1-abstract-full').style.display = 'none'; document.getElementById('2411.01893v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.24203">arXiv:2410.24203</a> <span> [<a href="https://arxiv.org/pdf/2410.24203">pdf</a>, <a href="https://arxiv.org/format/2410.24203">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+W">Weicai Ye</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+C">Chenhao Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zheng Chen</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyao Gao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xiaoshui Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Song-Hai Zhang</a>, <a href="/search/cs?searchtype=author&query=Ouyang%2C+W">Wanli Ouyang</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tong He</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Cairong Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.24203v1-abstract-short" style="display: inline;"> Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoram… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24203v1-abstract-full').style.display = 'inline'; document.getElementById('2410.24203v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.24203v1-abstract-full" style="display: none;"> Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24203v1-abstract-full').style.display = 'none'; document.getElementById('2410.24203v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS2024, Project: https://github.com/zju3dv/DiffPano; Code: https://github.com/zju3dv/DiffPano</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23690">arXiv:2410.23690</a> <span> [<a href="https://arxiv.org/pdf/2410.23690">pdf</a>, <a href="https://arxiv.org/format/2410.23690">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> XRDSLAM: A Flexible and Modular Framework for Deep Learning based SLAM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaomeng Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+N">Nan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23690v1-abstract-short" style="display: inline;"> In this paper, we propose a flexible SLAM framework, XRDSLAM. It adopts a modular code design and a multi-process running mechanism, providing highly reusable foundational modules such as unified dataset management, 3d visualization, algorithm configuration, and metrics evaluation. It can help developers quickly build a complete SLAM system, flexibly combine different algorithm modules, and conduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23690v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23690v1-abstract-full" style="display: none;"> In this paper, we propose a flexible SLAM framework, XRDSLAM. It adopts a modular code design and a multi-process running mechanism, providing highly reusable foundational modules such as unified dataset management, 3d visualization, algorithm configuration, and metrics evaluation. It can help developers quickly build a complete SLAM system, flexibly combine different algorithm modules, and conduct standardized benchmarking for accuracy and efficiency comparison. Within this framework, we integrate several state-of-the-art SLAM algorithms with different types, including NeRF and 3DGS based SLAM, and even odometry or reconstruction algorithms, which demonstrates the flexibility and extensibility. We also conduct a comprehensive comparison and evaluation of these integrated algorithms, analyzing the characteristics of each. Finally, we contribute all the code, configuration and data to the open-source community, which aims to promote the widespread research and development of SLAM technology within the open-source ecosystem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23690v1-abstract-full').style.display = 'none'; document.getElementById('2410.23690v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22733">arXiv:2410.22733</a> <span> [<a href="https://arxiv.org/pdf/2410.22733">pdf</a>, <a href="https://arxiv.org/format/2410.22733">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"> ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ni%2C+J">Junjie Ni</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Guanglin Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yijin Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhaoyang Huang</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+H">Hujun Bao</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="2410.22733v2-abstract-short" style="display: inline;"> We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local fe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22733v2-abstract-full').style.display = 'inline'; document.getElementById('2410.22733v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22733v2-abstract-full" style="display: none;"> We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local feature matching. This technique is built on constructing multiple homography hypotheses to approximate the continuous correspondence in the real world and uni-directional cross-attention to accelerate the refinement. On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods. Comprehensive evaluations on other open datasets such as Megadepth, ScanNet, and HPatches demonstrate our method's efficacy, highlighting its potential to significantly enhance a wide array of downstream applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22733v2-abstract-full').style.display = 'none'; document.getElementById('2410.22733v2-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22213">arXiv:2410.22213</a> <span> [<a href="https://arxiv.org/pdf/2410.22213">pdf</a>, <a href="https://arxiv.org/format/2410.22213">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"> LiVisSfM: Accurate and Robust Structure-from-Motion with LiDAR and Visual Cues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+H">Hanqing Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+L">Liyang Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhuang Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yihao Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.22213v1-abstract-short" style="display: inline;"> This paper presents an accurate and robust Structure-from-Motion (SfM) pipeline named LiVisSfM, which is an SfM-based reconstruction system that fully combines LiDAR and visual cues. Unlike most existing LiDAR-inertial odometry (LIO) and LiDAR-inertial-visual odometry (LIVO) methods relying heavily on LiDAR registration coupled with Inertial Measurement Unit (IMU), we propose a LiDAR-visual SfM me… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22213v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22213v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22213v1-abstract-full" style="display: none;"> This paper presents an accurate and robust Structure-from-Motion (SfM) pipeline named LiVisSfM, which is an SfM-based reconstruction system that fully combines LiDAR and visual cues. Unlike most existing LiDAR-inertial odometry (LIO) and LiDAR-inertial-visual odometry (LIVO) methods relying heavily on LiDAR registration coupled with Inertial Measurement Unit (IMU), we propose a LiDAR-visual SfM method which innovatively carries out LiDAR frame registration to LiDAR voxel map in a Point-to-Gaussian residual metrics, combined with a LiDAR-visual BA and explicit loop closure in a bundle optimization way to achieve accurate and robust LiDAR pose estimation without dependence on IMU incorporation. Besides, we propose an incremental voxel updating strategy for efficient voxel map updating during the process of LiDAR frame registration and LiDAR-visual BA optimization. Experiments demonstrate the superior effectiveness of our LiVisSfM framework over state-of-the-art LIO and LIVO works on more accurate and robust LiDAR pose recovery and dense point cloud reconstruction of both public KITTI benchmark and a variety of self-captured dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22213v1-abstract-full').style.display = 'none'; document.getElementById('2410.22213v1-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">18 pages, 9 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21157">arXiv:2410.21157</a> <span> [<a href="https://arxiv.org/pdf/2410.21157">pdf</a>, <a href="https://arxiv.org/format/2410.21157">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="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+K">Ken Deng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Congnan Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shukai Liu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">He Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+P">Peng Zhao</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+L">Linzheng Chai</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanan Wu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+K">Ke Jin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zekun Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoan Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+B">Bangyu Xiang</a>, <a href="/search/cs?searchtype=author&query=Su%2C+W">Wenbo Su</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+B">Bo Zheng</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="2410.21157v1-abstract-short" style="display: inline;"> Repository-level code completion has drawn great attention in software engineering, and several benchmark datasets have been introduced. However, existing repository-level code completion benchmarks usually focus on a limited number of languages (<5), which cannot evaluate the general code intelligence abilities across different languages for existing code Large Language Models (LLMs). Besides, th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21157v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21157v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21157v1-abstract-full" style="display: none;"> Repository-level code completion has drawn great attention in software engineering, and several benchmark datasets have been introduced. However, existing repository-level code completion benchmarks usually focus on a limited number of languages (<5), which cannot evaluate the general code intelligence abilities across different languages for existing code Large Language Models (LLMs). Besides, the existing benchmarks usually report overall average scores of different languages, where the fine-grained abilities in different completion scenarios are ignored. Therefore, to facilitate the research of code LLMs in multilingual scenarios, we propose a massively multilingual repository-level code completion benchmark covering 18 programming languages (called M2RC-EVAL), and two types of fine-grained annotations (i.e., bucket-level and semantic-level) on different completion scenarios are provided, where we obtain these annotations based on the parsed abstract syntax tree. Moreover, we also curate a massively multilingual instruction corpora M2RC- INSTRUCT dataset to improve the repository-level code completion abilities of existing code LLMs. Comprehensive experimental results demonstrate the effectiveness of our M2RC-EVAL and M2RC-INSTRUCT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21157v1-abstract-full').style.display = 'none'; document.getElementById('2410.21157v1-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">19 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20451">arXiv:2410.20451</a> <span> [<a href="https://arxiv.org/pdf/2410.20451">pdf</a>, <a href="https://arxiv.org/format/2410.20451">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"> BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yijin Li</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yichen Shen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhaoyang Huang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shuo Chen</a>, <a href="/search/cs?searchtype=author&query=Bian%2C+W">Weikang Bian</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xiaoyu Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fu-Yun Wang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+K">Keqiang Sun</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+H">Hujun Bao</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Z">Zhaopeng Cui</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongsheng 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="2410.20451v1-abstract-short" style="display: inline;"> Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and imag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20451v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20451v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20451v1-abstract-full" style="display: none;"> Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20451v1-abstract-full').style.display = 'none'; document.getElementById('2410.20451v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ECCV 2024. Project Page: https://www.blinkvision.net/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20424">arXiv:2410.20424</a> <span> [<a href="https://arxiv.org/pdf/2410.20424">pdf</a>, <a href="https://arxiv.org/format/2410.20424">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"> AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Ziming Li</a>, <a href="/search/cs?searchtype=author&query=Zang%2C+Q">Qianbo Zang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+D">David Ma</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jiawei Guo</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+T">Tuney Zheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Minghao Liu</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+X">Xinyao Niu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yue Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+W">Wanjun Zhong</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wangchunshu Zhou</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge 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="2410.20424v3-abstract-short" style="display: inline;"> Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and compreh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20424v3-abstract-full').style.display = 'inline'; document.getElementById('2410.20424v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20424v3-abstract-full" style="display: none;"> Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency. The framework offers highly customizable workflows, allowing users to intervene at each phase, thus integrating automated intelligence with human expertise. Our universal data science toolkit, comprising validated functions for data cleaning, feature engineering, and modeling, forms the foundation of this solution, enhancing productivity by streamlining common tasks. We selected 8 Kaggle competitions to simulate data processing workflows in real-world application scenarios. Evaluation results demonstrate that AutoKaggle achieves a validation submission rate of 0.85 and a comprehensive score of 0.82 in typical data science pipelines, fully proving its effectiveness and practicality in handling complex data science tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20424v3-abstract-full').style.display = 'none'; document.getElementById('2410.20424v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 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">44 pages, 10 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/2410.19723">arXiv:2410.19723</a> <span> [<a href="https://arxiv.org/pdf/2410.19723">pdf</a>, <a href="https://arxiv.org/format/2410.19723">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"> Sparse Decomposition of Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yaochen Hu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+M">Mai Zeng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Rumiantsev%2C+P">Pavel Rumiantsev</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+L">Liheng Ma</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yingxue Zhang</a>, <a href="/search/cs?searchtype=author&query=Coates%2C+M">Mark Coates</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="2410.19723v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This inference cost is the major obstacle to deploying GNN models with \emph{online prediction} to reflect the potentially dynamic node features. To address this, we propose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19723v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19723v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19723v1-abstract-full" style="display: none;"> Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This inference cost is the major obstacle to deploying GNN models with \emph{online prediction} to reflect the potentially dynamic node features. To address this, we propose an approach to reduce the number of nodes that are included during aggregation. We achieve this through a sparse decomposition, learning to approximate node representations using a weighted sum of linearly transformed features of a carefully selected subset of nodes within the extended neighbourhood. The approach achieves linear complexity with respect to the average node degree and the number of layers in the graph neural network. We introduce an algorithm to compute the optimal parameters for the sparse decomposition, ensuring an accurate approximation of the original GNN model, and present effective strategies to reduce the training time and improve the learning process. We demonstrate via extensive experiments that our method outperforms other baselines designed for inference speedup, achieving significant accuracy gains with comparable inference times for both node classification and spatio-temporal forecasting tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19723v1-abstract-full').style.display = 'none'; document.getElementById('2410.19723v1-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/2410.18856">arXiv:2410.18856</a> <span> [<a href="https://arxiv.org/pdf/2410.18856">pdf</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"> Demystifying Large Language Models for Medicine: A Primer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jin%2C+Q">Qiao Jin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+N">Nicholas Wan</a>, <a href="/search/cs?searchtype=author&query=Leaman%2C+R">Robert Leaman</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+S">Shubo Tian</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhizheng Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yifan Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zifeng Wang</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+G">Guangzhi Xiong</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+P">Po-Ting Lai</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Qingqing Zhu</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+B">Benjamin Hou</a>, <a href="/search/cs?searchtype=author&query=Sarfo-Gyamfi%2C+M">Maame Sarfo-Gyamfi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gongbo Zhang</a>, <a href="/search/cs?searchtype=author&query=Gilson%2C+A">Aidan Gilson</a>, <a href="/search/cs?searchtype=author&query=Bhasuran%2C+B">Balu Bhasuran</a>, <a href="/search/cs?searchtype=author&query=He%2C+Z">Zhe He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Aidong Zhang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jimeng Sun</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+C">Chunhua Weng</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+R+M">Ronald M. Summers</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qingyu Chen</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Y">Yifan Peng</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Zhiyong Lu</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="2410.18856v3-abstract-short" style="display: inline;"> Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering me… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18856v3-abstract-full').style.display = 'inline'; document.getElementById('2410.18856v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18856v3-abstract-full" style="display: none;"> Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18856v3-abstract-full').style.display = 'none'; document.getElementById('2410.18856v3-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">v1</span> submitted 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18433">arXiv:2410.18433</a> <span> [<a href="https://arxiv.org/pdf/2410.18433">pdf</a>, <a href="https://arxiv.org/format/2410.18433">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"> Segmentation-aware Prior Assisted Joint Global Information Aggregated 3D Building Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hongxin Peng</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+Y">Yongjian Liao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Weijun Li</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+C">Chuanyu Fu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoxin Zhang</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Ziquan Ding</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zijie Huang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Q">Qiku Cao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+S">Shuting Cai</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="2410.18433v1-abstract-short" style="display: inline;"> Multi-View Stereo plays a pivotal role in civil engineering by facilitating 3D modeling, precise engineering surveying, quantitative analysis, as well as monitoring and maintenance. It serves as a valuable tool, offering high-precision and real-time spatial information crucial for various engineering projects. However, Multi-View Stereo algorithms encounter challenges in reconstructing weakly-text… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18433v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18433v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18433v1-abstract-full" style="display: none;"> Multi-View Stereo plays a pivotal role in civil engineering by facilitating 3D modeling, precise engineering surveying, quantitative analysis, as well as monitoring and maintenance. It serves as a valuable tool, offering high-precision and real-time spatial information crucial for various engineering projects. However, Multi-View Stereo algorithms encounter challenges in reconstructing weakly-textured regions within large-scale building scenes. In these areas, the stereo matching of pixels often fails, leading to inaccurate depth estimations. Based on the Segment Anything Model and RANSAC algorithm, we propose an algorithm that accurately segments weakly-textured regions and constructs their plane priors. These plane priors, combined with triangulation priors, form a reliable prior candidate set. Additionally, we introduce a novel global information aggregation cost function. This function selects optimal plane prior information based on global information in the prior candidate set, constrained by geometric consistency during the depth estimation update process. Experimental results on both the ETH3D benchmark dataset, aerial dataset, building dataset and real scenarios substantiate the superior performance of our method in producing 3D building models compared to other state-of-the-art methods. In summary, our work aims to enhance the completeness and density of 3D building reconstruction, carrying implications for broader applications in urban planning and virtual reality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18433v1-abstract-full').style.display = 'none'; document.getElementById('2410.18433v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 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/2410.17885">arXiv:2410.17885</a> <span> [<a href="https://arxiv.org/pdf/2410.17885">pdf</a>, <a href="https://arxiv.org/format/2410.17885">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deng%2C+L">Linger Deng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuliang Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bohan Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+D">Dongliang Luo</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L">Liang Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chengquan Zhang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+P">Pengyuan Lyu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Ziyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gang Zhang</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+E">Errui Ding</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yingying Zhu</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+X">Xiang Bai</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="2410.17885v2-abstract-short" style="display: inline;"> Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity. To synthesize higher-quality data… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17885v2-abstract-full').style.display = 'inline'; document.getElementById('2410.17885v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17885v2-abstract-full" style="display: none;"> Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity. To synthesize higher-quality data, we propose a two-stage Reverse Chain-of-Thought (R-CoT) geometry problem generation pipeline. First, we introduce GeoChain to produce high-fidelity geometric images and corresponding descriptions highlighting relations among geometric elements. We then design a Reverse A&Q method that reasons step-by-step based on the descriptions and generates questions in reverse from the reasoning results. Experiments demonstrate that the proposed method brings significant and consistent improvements on multiple LMM baselines, achieving new performance records in the 2B, 7B, and 8B settings. Notably, R-CoT-8B significantly outperforms previous state-of-the-art open-source mathematical models by 16.6% on MathVista and 9.2% on GeoQA, while also surpassing the closed-source model GPT-4o by an average of 13% across both datasets. The code is available at https://github.com/dle666/R-CoT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17885v2-abstract-full').style.display = 'none'; document.getElementById('2410.17885v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16430">arXiv:2410.16430</a> <span> [<a href="https://arxiv.org/pdf/2410.16430">pdf</a>, <a href="https://arxiv.org/format/2410.16430">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"> HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhiming Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guanhua Zhang</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+Z">Zheming Yin</a>, <a href="/search/cs?searchtype=author&query=Haeufle%2C+D">Daniel Haeufle</a>, <a href="/search/cs?searchtype=author&query=Schmitt%2C+S">Syn Schmitt</a>, <a href="/search/cs?searchtype=author&query=Bulling%2C+A">Andreas Bulling</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="2410.16430v1-abstract-short" style="display: inline;"> Human hand and head movements are the most pervasive input modalities in extended reality (XR) and are significant for a wide range of applications. However, prior works on hand and head modelling in XR only explored a single modality or focused on specific applications. We present HaHeAE - a novel self-supervised method for learning generalisable joint representations of hand and head movements i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16430v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16430v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16430v1-abstract-full" style="display: none;"> Human hand and head movements are the most pervasive input modalities in extended reality (XR) and are significant for a wide range of applications. However, prior works on hand and head modelling in XR only explored a single modality or focused on specific applications. We present HaHeAE - a novel self-supervised method for learning generalisable joint representations of hand and head movements in XR. At the core of our method is an autoencoder (AE) that uses a graph convolutional network-based semantic encoder and a diffusion-based stochastic encoder to learn the joint semantic and stochastic representations of hand-head movements. It also features a diffusion-based decoder to reconstruct the original signals. Through extensive evaluations on three public XR datasets, we show that our method 1) significantly outperforms commonly used self-supervised methods by up to 74.0% in terms of reconstruction quality and is generalisable across users, activities, and XR environments, 2) enables new applications, including interpretable hand-head cluster identification and variable hand-head movement generation, and 3) can serve as an effective feature extractor for downstream tasks. Together, these results demonstrate the effectiveness of our method and underline the potential of self-supervised methods for jointly modelling hand-head behaviours in extended reality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16430v1-abstract-full').style.display = 'none'; document.getElementById('2410.16430v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15686">arXiv:2410.15686</a> <span> [<a href="https://arxiv.org/pdf/2410.15686">pdf</a>, <a href="https://arxiv.org/format/2410.15686">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> NetSafe: Exploring the Topological Safety of Multi-agent Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+M">Miao Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shilong Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guibin Zhang</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+J">Junyuan Mao</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+C">Chenlong Yin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qijiong Liu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Q">Qingsong Wen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kun Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yang 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="2410.15686v1-abstract-short" style="display: inline;"> Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information remains unexplored with previous research on single LLM's safety be challenging to transfer. In this paper, we focus on the safety of multi-agent networks from a topo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15686v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15686v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15686v1-abstract-full" style="display: none;"> Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information remains unexplored with previous research on single LLM's safety be challenging to transfer. In this paper, we focus on the safety of multi-agent networks from a topological perspective, investigating which topological properties contribute to safer networks. To this end, we propose a general framework, NetSafe along with an iterative RelCom interaction to unify existing diverse LLM-based agent frameworks, laying the foundation for generalized topological safety research. We identify several critical phenomena when multi-agent networks are exposed to attacks involving misinformation, bias, and harmful information, termed as Agent Hallucination and Aggregation Safety. Furthermore, we find that highly connected networks are more susceptible to the spread of adversarial attacks, with task performance in a Star Graph Topology decreasing by 29.7%. Besides, our proposed static metrics aligned more closely with real-world dynamic evaluations than traditional graph-theoretic metrics, indicating that networks with greater average distances from attackers exhibit enhanced safety. In conclusion, our work introduces a new topological perspective on the safety of LLM-based multi-agent networks and discovers several unreported phenomena, paving the way for future research to explore the safety of such networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15686v1-abstract-full').style.display = 'none'; document.getElementById('2410.15686v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13854">arXiv:2410.13854</a> <span> [<a href="https://arxiv.org/pdf/2410.13854">pdf</a>, <a href="https://arxiv.org/format/2410.13854">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Can MLLMs Understand the Deep Implication Behind Chinese Images? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenhao Zhang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+X">Xi Feng</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+Y">Yuelin Bai</a>, <a href="/search/cs?searchtype=author&query=Du%2C+X">Xinrun Du</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+J">Jinchang Hou</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+K">Kaixin Deng</a>, <a href="/search/cs?searchtype=author&query=Han%2C+G">Guangzeng Han</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qinrui Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bingli Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+X">Xingwei Qu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yifei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Q">Qixuan Zhao</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yiming Liang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Ziqiang Liu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+F">Feiteng Fang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Min Yang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chenghua Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Ni%2C+S">Shiwen Ni</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="2410.13854v1-abstract-short" style="display: inline;"> As the capabilities of Multimodal Large Language Models (MLLMs) continue to improve, the need for higher-order capability evaluation of MLLMs is increasing. However, there is a lack of work evaluating MLLM for higher-order perception and understanding of Chinese visual content. To fill the gap, we introduce the **C**hinese **I**mage **I**mplication understanding **Bench**mark, **CII-Bench**, which… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13854v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13854v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13854v1-abstract-full" style="display: none;"> As the capabilities of Multimodal Large Language Models (MLLMs) continue to improve, the need for higher-order capability evaluation of MLLMs is increasing. However, there is a lack of work evaluating MLLM for higher-order perception and understanding of Chinese visual content. To fill the gap, we introduce the **C**hinese **I**mage **I**mplication understanding **Bench**mark, **CII-Bench**, which aims to assess the higher-order perception and understanding capabilities of MLLMs for Chinese images. CII-Bench stands out in several ways compared to existing benchmarks. Firstly, to ensure the authenticity of the Chinese context, images in CII-Bench are sourced from the Chinese Internet and manually reviewed, with corresponding answers also manually crafted. Additionally, CII-Bench incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, which can deeply reflect the model's understanding of Chinese traditional culture. Through extensive experiments on CII-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on CII-Bench. The highest accuracy of MLLMs attains 64.4%, where as human accuracy averages 78.2%, peaking at an impressive 81.0%. Subsequently, MLLMs perform worse on Chinese traditional culture images, suggesting limitations in their ability to understand high-level semantics and lack a deep knowledge base of Chinese traditional culture. Finally, it is observed that most models exhibit enhanced accuracy when image emotion hints are incorporated into the prompts. We believe that CII-Bench will enable MLLMs to gain a better understanding of Chinese semantics and Chinese-specific images, advancing the journey towards expert artificial general intelligence (AGI). Our project is publicly available at https://cii-bench.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13854v1-abstract-full').style.display = 'none'; document.getElementById('2410.13854v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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">32 pages,18 figures. Project Page: https://cii-bench.github.io/ Code: https://github.com/MING_X/CII-Bench Dataset: https://huggingface.co/datasets/m-a-p/CII-Bench</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13761">arXiv:2410.13761</a> <span> [<a href="https://arxiv.org/pdf/2410.13761">pdf</a>, <a href="https://arxiv.org/format/2410.13761">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"> GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guibin Zhang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+H">Haonan Dong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhixun Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dingshuo Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kai Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tianlong Chen</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">Dawei Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kun 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="2410.13761v1-abstract-short" style="display: inline;"> Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by retaining, synthesizing, or selecting a small yet informative subset from the full set. Among these methods, data pruning incurs the least additional training cos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13761v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13761v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13761v1-abstract-full" style="display: none;"> Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by retaining, synthesizing, or selecting a small yet informative subset from the full set. Among these methods, data pruning incurs the least additional training cost and offers the most practical acceleration benefits. However, it is the most vulnerable, often suffering significant performance degradation with imbalanced or biased data schema, thus raising concerns about its accuracy and reliability in on-device deployment. Therefore, there is a looming need for a new data pruning paradigm that maintains the efficiency of previous practices while ensuring balance and robustness. Unlike the fields of computer vision and natural language processing, where mature solutions have been developed to address these issues, graph neural networks (GNNs) continue to struggle with increasingly large-scale, imbalanced, and noisy datasets, lacking a unified dataset pruning solution. To achieve this, we introduce a novel dynamic soft-pruning method, GDeR, designed to update the training ``basket'' during the process using trainable prototypes. GDeR first constructs a well-modeled graph embedding hypersphere and then samples \textit{representative, balanced, and unbiased subsets} from this embedding space, which achieves the goal we called Graph Training Debugging. Extensive experiments on five datasets across three GNN backbones, demonstrate that GDeR (I) achieves or surpasses the performance of the full dataset with 30%~50% fewer training samples, (II) attains up to a 2.81x lossless training speedup, and (III) outperforms state-of-the-art pruning methods in imbalanced training and noisy training scenarios by 0.3%~4.3% and 3.6%~7.8%, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13761v1-abstract-full').style.display = 'none'; document.getElementById('2410.13761v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13733">arXiv:2410.13733</a> <span> [<a href="https://arxiv.org/pdf/2410.13733">pdf</a>, <a href="https://arxiv.org/format/2410.13733">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="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Improving Multi-modal Large Language Model through Boosting Vision Capabilities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yanpeng Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Huaxin Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qiang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Sang%2C+N">Nong Sang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gang Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingdong Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zechao 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="2410.13733v1-abstract-short" style="display: inline;"> We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13733v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13733v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13733v1-abstract-full" style="display: none;"> We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13733v1-abstract-full').style.display = 'none'; document.getElementById('2410.13733v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13639">arXiv:2410.13639</a> <span> [<a href="https://arxiv.org/pdf/2410.13639">pdf</a>, <a href="https://arxiv.org/format/2410.13639">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"> A Comparative Study on Reasoning Patterns of OpenAI's o1 Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Siwei Wu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Z">Zhongyuan Peng</a>, <a href="/search/cs?searchtype=author&query=Du%2C+X">Xinrun Du</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+T">Tuney Zheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Minghao Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jialong Wu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+J">Jiachen Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yizhi Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wangchunshu Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qunshu Lin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Junbo Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chenghua Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+H">J. H. 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="2410.13639v2-abstract-short" style="display: inline;"> Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, merely increasing the number of model parameters yields diminishing performance improvements and heavy computational costs. Recently, OpenAI's o1 model has shown that inference strategies (i.e., Test-time Compute methods) c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13639v2-abstract-full').style.display = 'inline'; document.getElementById('2410.13639v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13639v2-abstract-full" style="display: none;"> Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, merely increasing the number of model parameters yields diminishing performance improvements and heavy computational costs. Recently, OpenAI's o1 model has shown that inference strategies (i.e., Test-time Compute methods) can also significantly enhance the reasoning capabilities of LLMs. However, the mechanisms behind these methods are still unexplored. In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i.e., math, coding, commonsense reasoning). Specifically, first, our experiments show that the o1 model has achieved the best performance on most datasets. Second, as for the methods of searching diverse responses (e.g., BoN), we find the reward models' capability and the search space both limit the upper boundary of these methods. Third, as for the methods that break the problem into many sub-problems, the Agent Workflow has achieved better performance than Step-wise BoN due to the domain-specific system prompt for planning better reasoning processes. Fourth, it is worth mentioning that we have summarized six reasoning patterns of o1, and provided a detailed analysis on several reasoning benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13639v2-abstract-full').style.display = 'none'; document.getElementById('2410.13639v2-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">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13471">arXiv:2410.13471</a> <span> [<a href="https://arxiv.org/pdf/2410.13471">pdf</a>, <a href="https://arxiv.org/format/2410.13471">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"> SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bin Wang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+F">Fei Deng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuang Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+W">Wen Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhixuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gulan Zhang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+P">Peifan Jiang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13471v2-abstract-short" style="display: inline;"> Semantic segmentation of remote sensing (RS) images is a challenging yet crucial task. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field, acquiring high-quality labeled data is expensive and time-consuming. Additionally, variations in ground sampling distance, imaging equipment, and geographic differences cause domain shi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13471v2-abstract-full').style.display = 'inline'; document.getElementById('2410.13471v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13471v2-abstract-full" style="display: none;"> Semantic segmentation of remote sensing (RS) images is a challenging yet crucial task. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field, acquiring high-quality labeled data is expensive and time-consuming. Additionally, variations in ground sampling distance, imaging equipment, and geographic differences cause domain shifts between datasets, which limit model performance across domains. Unsupervised domain adaptation (UDA) offers a solution by enabling models to learn from unlabeled target domain data while training on labeled source domain data. Recent self-supervised learning approaches using pseudo-label generation have shown promise in addressing domain discrepancies. Combining source and target images with their true and pseudo labels has proven effective in reducing domain bias. However, the use of pseudo-labeling for RS image segmentation is underexplored. Existing methods often rely on high-confidence pixel points as pseudo-labels, reducing supervision in low-confidence areas. Noise in pseudo-labels further weakens the model's ability to learn target domain semantics. While some methods assign confidence weights, noisy pseudo-labels remain an issue. To address these limitations, we propose integrating contrastive learning into UDA, enhancing the model's capacity to capture semantic information by maximizing the similarity between augmented views of the same image. This provides additional supervision to improve performance in the target domain. Extensive experiments on key RS datasets (Potsdam, Vaihingen, LoveDA) demonstrate that our SimSeg method outperforms existing approaches, achieving state-of-the-art results. Visualization and quantitative analyses confirm its superior ability to learn from the target domain. The code is available at \url{https://github.com/woldier/SiamSeg}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13471v2-abstract-full').style.display = 'none'; document.getElementById('2410.13471v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13267">arXiv:2410.13267</a> <span> [<a href="https://arxiv.org/pdf/2410.13267">pdf</a>, <a href="https://arxiv.org/format/2410.13267">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shangda Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yashan Wang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+R">Ruibin Yuan</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Zhancheng Guo</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+X">Xu Tan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+M">Monan Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jing Chen</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+X">Xuefeng Mu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yuejie Gao</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yuanliang Dong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiafeng Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaobing Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+F">Feng Yu</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="2410.13267v1-abstract-short" style="display: inline;"> Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13267v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13267v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13267v1-abstract-full" style="display: none;"> Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (Musical Instrument Digital Interface) for music information retrieval. CLaMP 2, pre-trained on 1.5 million ABC-MIDI-text triplets, includes a multilingual text encoder and a multimodal music encoder aligned via contrastive learning. By leveraging large language models, we obtain refined and consistent multilingual descriptions at scale, significantly reducing textual noise and balancing language distribution. Our experiments show that CLaMP 2 achieves state-of-the-art results in both multilingual semantic search and music classification across modalities, thus establishing a new standard for inclusive and global music information retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13267v1-abstract-full').style.display = 'none'; document.getElementById('2410.13267v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 10 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12366">arXiv:2410.12366</a> <span> [<a href="https://arxiv.org/pdf/2410.12366">pdf</a>, <a href="https://arxiv.org/format/2410.12366">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"> Multi-Cause Deconfounding for Recommender Systems with Latent Confounders </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhirong Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shichao Zhang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">Debo Cheng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiuyong Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lin Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guixian 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="2410.12366v1-abstract-short" style="display: inline;"> In recommender systems, various latent confounding factors (e.g., user social environment and item public attractiveness) can affect user behavior, item exposure, and feedback in distinct ways. These factors may directly or indirectly impact user feedback and are often shared across items or users, making them multi-cause latent confounders. However, existing methods typically fail to account for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12366v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12366v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12366v1-abstract-full" style="display: none;"> In recommender systems, various latent confounding factors (e.g., user social environment and item public attractiveness) can affect user behavior, item exposure, and feedback in distinct ways. These factors may directly or indirectly impact user feedback and are often shared across items or users, making them multi-cause latent confounders. However, existing methods typically fail to account for latent confounders between users and their feedback, as well as those between items and user feedback simultaneously. To address the problem of multi-cause latent confounders, we propose a multi-cause deconfounding method for recommender systems with latent confounders (MCDCF). MCDCF leverages multi-cause causal effect estimation to learn substitutes for latent confounders associated with both users and items, using user behaviour data. Specifically, MCDCF treats the multiple items that users interact with and the multiple users that interact with items as treatment variables, enabling it to learn substitutes for the latent confounders that influence the estimation of causality between users and their feedback, as well as between items and user feedback. Additionally, we theoretically demonstrate the soundness of our MCDCF method. Extensive experiments on three real-world datasets demonstrate that our MCDCF method effectively recovers latent confounders related to users and items, reducing bias and thereby improving recommendation accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12366v1-abstract-full').style.display = 'none'; document.getElementById('2410.12366v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11913">arXiv:2410.11913</a> <span> [<a href="https://arxiv.org/pdf/2410.11913">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Development and Testing of a Wood Panels Bark Removal Equipment Based on Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+R">Rijun Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guanghao Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongyang Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xinye Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yesheng Chen</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+F">Fulong Liang</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+X">Xiangwei Mou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bo 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="2410.11913v1-abstract-short" style="display: inline;"> Attempting to apply deep learning methods to wood panels bark removal equipment to enhance the quality and efficiency of bark removal is a significant and challenging endeavor. This study develops and tests a deep learning-based wood panels bark removal equipment. In accordance with the practical requirements of sawmills, a wood panels bark removal equipment equipped with a vision inspection syste… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11913v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11913v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11913v1-abstract-full" style="display: none;"> Attempting to apply deep learning methods to wood panels bark removal equipment to enhance the quality and efficiency of bark removal is a significant and challenging endeavor. This study develops and tests a deep learning-based wood panels bark removal equipment. In accordance with the practical requirements of sawmills, a wood panels bark removal equipment equipped with a vision inspection system is designed. Based on a substantial collection of wood panel images obtained using the visual inspection system, the first general wood panels semantic segmentation dataset is constructed for training the BiSeNetV1 model employed in this study. Furthermore, the calculation methods and processes for the essential key data required in the bark removal process are presented in detail. Comparative experiments of the BiSeNetV1 model and tests of bark removal effectiveness are conducted in both laboratory and sawmill environments. The results of the comparative experiments indicate that the application of the BiSeNetV1 segmentation model is rational and feasible. The results of the bark removal effectiveness tests demonstrate a significant improvement in both the quality and efficiency of bark removal. The developed equipment fully meets the sawmill's requirements for precision and efficiency in bark removal processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11913v1-abstract-full').style.display = 'none'; document.getElementById('2410.11913v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11782">arXiv:2410.11782</a> <span> [<a href="https://arxiv.org/pdf/2410.11782">pdf</a>, <a href="https://arxiv.org/format/2410.11782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guibin Zhang</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+Y">Yanwei Yue</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xiangguo Sun</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+G">Guancheng Wan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+M">Miao Yu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Junfeng Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kun Wang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">Dawei Cheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.11782v1-abstract-short" style="display: inline;"> Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11782v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11782v1-abstract-full" style="display: none;"> Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11782v1-abstract-full').style.display = 'none'; document.getElementById('2410.11782v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11710">arXiv:2410.11710</a> <span> [<a href="https://arxiv.org/pdf/2410.11710">pdf</a>, <a href="https://arxiv.org/format/2410.11710">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"> MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pei Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanan Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zekun Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Song%2C+X">Xiaoshuai Song</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Z">Zhongyuan Peng</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+K">Ken Deng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiakai Wang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Junran Peng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hangyu Guo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Su%2C+W">Wenbo Su</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+B">Bo Zheng</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="2410.11710v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing datasets have the following limitations: (1). Insufficient evaluation scenarios (e.g., only cover limited tool-use scenes). (2). Extensive evaluation costs (e.g., GPT… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11710v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11710v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11710v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing datasets have the following limitations: (1). Insufficient evaluation scenarios (e.g., only cover limited tool-use scenes). (2). Extensive evaluation costs (e.g., GPT API costs). To address these limitations, in this work, we propose a multi-granularity tool-use benchmark for large language models called MTU-Bench. For the "multi-granularity" property, our MTU-Bench covers five tool usage scenes (i.e., single-turn and single-tool, single-turn and multiple-tool, multiple-turn and single-tool, multiple-turn and multiple-tool, and out-of-distribution tasks). Besides, all evaluation metrics of our MTU-Bench are based on the prediction results and the ground truth without using any GPT or human evaluation metrics. Moreover, our MTU-Bench is collected by transforming existing high-quality datasets to simulate real-world tool usage scenarios, and we also propose an instruction dataset called MTU-Instruct data to enhance the tool-use abilities of existing LLMs. Comprehensive experimental results demonstrate the effectiveness of our MTU-Bench. Code and data will be released at https: //github.com/MTU-Bench-Team/MTU-Bench.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11710v1-abstract-full').style.display = 'none'; document.getElementById('2410.11710v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11493">arXiv:2410.11493</a> <span> [<a href="https://arxiv.org/pdf/2410.11493">pdf</a>, <a href="https://arxiv.org/format/2410.11493">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Towards Fair Graph Representation Learning in Social Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guixian Zhang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+G">Guan Yuan</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">Debo Cheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lin Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiuyong Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shichao 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="2410.11493v2-abstract-short" style="display: inline;"> With the widespread use of Graph Neural Networks (GNNs) for representation learning from network data, the fairness of GNN models has raised great attention lately. Fair GNNs aim to ensure that node representations can be accurately classified, but not easily associated with a specific group. Existing advanced approaches essentially enhance the generalisation of node representation in combination… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11493v2-abstract-full').style.display = 'inline'; document.getElementById('2410.11493v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11493v2-abstract-full" style="display: none;"> With the widespread use of Graph Neural Networks (GNNs) for representation learning from network data, the fairness of GNN models has raised great attention lately. Fair GNNs aim to ensure that node representations can be accurately classified, but not easily associated with a specific group. Existing advanced approaches essentially enhance the generalisation of node representation in combination with data augmentation strategy, and do not directly impose constraints on the fairness of GNNs. In this work, we identify that a fundamental reason for the unfairness of GNNs in social network learning is the phenomenon of social homophily, i.e., users in the same group are more inclined to congregate. The message-passing mechanism of GNNs can cause users in the same group to have similar representations due to social homophily, leading model predictions to establish spurious correlations with sensitive attributes. Inspired by this reason, we propose a method called Equity-Aware GNN (EAGNN) towards fair graph representation learning. Specifically, to ensure that model predictions are independent of sensitive attributes while maintaining prediction performance, we introduce constraints for fair representation learning based on three principles: sufficiency, independence, and separation. We theoretically demonstrate that our EAGNN method can effectively achieve group fairness. Extensive experiments on three datasets with varying levels of social homophily illustrate that our EAGNN method achieves the state-of-the-art performance across two fairness metrics and offers competitive effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11493v2-abstract-full').style.display = 'none'; document.getElementById('2410.11493v2-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">v1</span> submitted 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11236">arXiv:2410.11236</a> <span> [<a href="https://arxiv.org/pdf/2410.11236">pdf</a>, <a href="https://arxiv.org/format/2410.11236">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"> Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guiyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+H">Huan-ang Gao</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zijian Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hao Zhao</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zhedong Zheng</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="2410.11236v1-abstract-short" style="display: inline;"> In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their semantic alignment with the provided conditions. To tackle this issue, previous studies have employed supervised perceptual losses derived from pre-trained mod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11236v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11236v1-abstract-full" style="display: none;"> In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their semantic alignment with the provided conditions. To tackle this issue, previous studies have employed supervised perceptual losses derived from pre-trained models, i.e., reward models, to enforce alignment between the condition and the generated result. However, we observe one inherent shortcoming: considering the diversity of synthesized images, the reward model usually provides inaccurate feedback when encountering newly generated data, which can undermine the training process. To address this limitation, we propose an uncertainty-aware reward modeling, called Ctrl-U, including uncertainty estimation and uncertainty-aware regularization, designed to reduce the adverse effects of imprecise feedback from the reward model. Given the inherent cognitive uncertainty within reward models, even images generated under identical conditions often result in a relatively large discrepancy in reward loss. Inspired by the observation, we explicitly leverage such prediction variance as an uncertainty indicator. Based on the uncertainty estimation, we regularize the model training by adaptively rectifying the reward. In particular, rewards with lower uncertainty receive higher loss weights, while those with higher uncertainty are given reduced weights to allow for larger variability. The proposed uncertainty regularization facilitates reward fine-tuning through consistency construction. Extensive experiments validate the effectiveness of our methodology in improving the controllability and generation quality, as well as its scalability across diverse conditional scenarios. Code will soon be available at https://grenoble-zhang.github.io/Ctrl-U-Page/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11236v1-abstract-full').style.display = 'none'; document.getElementById('2410.11236v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">Preprint. 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/2410.10241">arXiv:2410.10241</a> <span> [<a href="https://arxiv.org/pdf/2410.10241">pdf</a>, <a href="https://arxiv.org/format/2410.10241">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Jintang Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+R">Ruofan Wu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuchang Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Huizhe Zhang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+X">Xinzhou Jin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guibin Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zulun Zhu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zibin Zheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Liang Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.10241v1-abstract-short" style="display: inline;"> Graph autoencoders (GAEs) are self-supervised learning models that can learn meaningful representations of graph-structured data by reconstructing the input graph from a low-dimensional latent space. Over the past few years, GAEs have gained significant attention in academia and industry. In particular, the recent advent of GAEs with masked autoencoding schemes marks a significant advancement in g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10241v1-abstract-full').style.display = 'inline'; document.getElementById('2410.10241v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10241v1-abstract-full" style="display: none;"> Graph autoencoders (GAEs) are self-supervised learning models that can learn meaningful representations of graph-structured data by reconstructing the input graph from a low-dimensional latent space. Over the past few years, GAEs have gained significant attention in academia and industry. In particular, the recent advent of GAEs with masked autoencoding schemes marks a significant advancement in graph self-supervised learning research. While numerous GAEs have been proposed, the underlying mechanisms of GAEs are not well understood, and a comprehensive benchmark for GAEs is still lacking. In this work, we bridge the gap between GAEs and contrastive learning by establishing conceptual and methodological connections. We revisit the GAEs studied in previous works and demonstrate how contrastive learning principles can be applied to GAEs. Motivated by these insights, we introduce lrGAE (left-right GAE), a general and powerful GAE framework that leverages contrastive learning principles to learn meaningful representations. Our proposed lrGAE not only facilitates a deeper understanding of GAEs but also sets a new benchmark for GAEs across diverse graph-based learning tasks. The source code for lrGAE, including the baselines and all the code for reproducing the results, is publicly available at https://github.com/EdisonLeeeee/lrGAE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10241v1-abstract-full').style.display = 'none'; document.getElementById('2410.10241v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">Preprint, under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08914">arXiv:2410.08914</a> <span> [<a href="https://arxiv.org/pdf/2410.08914">pdf</a>, <a href="https://arxiv.org/format/2410.08914">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="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> An End-to-End Deep Learning Method for Solving Nonlocal Allen-Cahn and Cahn-Hilliard Phase-Field Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Geng%2C+Y">Yuwei Geng</a>, <a href="/search/cs?searchtype=author&query=Burkovska%2C+O">Olena Burkovska</a>, <a href="/search/cs?searchtype=author&query=Ju%2C+L">Lili Ju</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guannan Zhang</a>, <a href="/search/cs?searchtype=author&query=Gunzburger%2C+M">Max Gunzburger</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="2410.08914v1-abstract-short" style="display: inline;"> We propose an efficient end-to-end deep learning method for solving nonlocal Allen-Cahn (AC) and Cahn-Hilliard (CH) phase-field models. One motivation for this effort emanates from the fact that discretized partial differential equation-based AC or CH phase-field models result in diffuse interfaces between phases, with the only recourse for remediation is to severely refine the spatial grids in th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08914v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08914v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08914v1-abstract-full" style="display: none;"> We propose an efficient end-to-end deep learning method for solving nonlocal Allen-Cahn (AC) and Cahn-Hilliard (CH) phase-field models. One motivation for this effort emanates from the fact that discretized partial differential equation-based AC or CH phase-field models result in diffuse interfaces between phases, with the only recourse for remediation is to severely refine the spatial grids in the vicinity of the true moving sharp interface whose width is determined by a grid-independent parameter that is substantially larger than the local grid size. In this work, we introduce non-mass conserving nonlocal AC or CH phase-field models with regular, logarithmic, or obstacle double-well potentials. Because of non-locality, some of these models feature totally sharp interfaces separating phases. The discretization of such models can lead to a transition between phases whose width is only a single grid cell wide. Another motivation is to use deep learning approaches to ameliorate the otherwise high cost of solving discretized nonlocal phase-field models. To this end, loss functions of the customized neural networks are defined using the residual of the fully discrete approximations of the AC or CH models, which results from applying a Fourier collocation method and a temporal semi-implicit approximation. To address the long-range interactions in the models, we tailor the architecture of the neural network by incorporating a nonlocal kernel as an input channel to the neural network model. We then provide the results of extensive computational experiments to illustrate the accuracy, structure-preserving properties, predictive capabilities, and cost reductions of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08914v1-abstract-full').style.display = 'none'; document.getElementById('2410.08914v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08356">arXiv:2410.08356</a> <span> [<a href="https://arxiv.org/pdf/2410.08356">pdf</a>, <a href="https://arxiv.org/format/2410.08356">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"> SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guanhua Zhang</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+M">Mohamed Ahmed</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhiming Hu</a>, <a href="/search/cs?searchtype=author&query=Bulling%2C+A">Andreas Bulling</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="2410.08356v1-abstract-short" style="display: inline;"> Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08356v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08356v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08356v1-abstract-full" style="display: none;"> Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summarise low-level input actions into high-level intentions. SummAct first identifies sub-goals from user actions using a large language model and in-context learning. High-level intentions are then obtained by fine-tuning the model using a novel UI element attention to preserve detailed context information embedded within UI elements during summarisation. Through a series of evaluations, we demonstrate that SummAct significantly outperforms baselines across desktop and mobile interfaces as well as interactive tasks by up to 21.9%. We further show three exciting interactive applications benefited from SummAct: interactive behaviour forecasting, automatic behaviour synonym identification, and language-based behaviour retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08356v1-abstract-full').style.display = 'none'; document.getElementById('2410.08356v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07985">arXiv:2410.07985</a> <span> [<a href="https://arxiv.org/pdf/2410.07985">pdf</a>, <a href="https://arxiv.org/format/2410.07985">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"> Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+B">Bofei Gao</a>, <a href="/search/cs?searchtype=author&query=Song%2C+F">Feifan Song</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhe Yang</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Z">Zefan Cai</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+Y">Yibo Miao</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Q">Qingxiu Dong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lei Li</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+C">Chenghao Ma</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Liang Chen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+R">Runxin Xu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Z">Zhengyang Tang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Benyou Wang</a>, <a href="/search/cs?searchtype=author&query=Zan%2C+D">Daoguang Zan</a>, <a href="/search/cs?searchtype=author&query=Quan%2C+S">Shanghaoran Quan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Sha%2C+L">Lei Sha</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yichang Zhang</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xuancheng Ren</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tianyu Liu</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+B">Baobao Chang</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="2410.07985v2-abstract-short" style="display: inline;"> Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging bench… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07985v2-abstract-full').style.display = 'inline'; document.getElementById('2410.07985v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07985v2-abstract-full" style="display: none;"> Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems are meticulously categorized into over 33 sub-domains and span more than 10 distinct difficulty levels, enabling a holistic assessment of model performance in Olympiad-mathematical reasoning. Furthermore, we conducted an in-depth analysis based on this benchmark. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54% and 52.55% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07985v2-abstract-full').style.display = 'none'; document.getElementById('2410.07985v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 Pages, 17 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/2410.06892">arXiv:2410.06892</a> <span> [<a href="https://arxiv.org/pdf/2410.06892">pdf</a>, <a href="https://arxiv.org/format/2410.06892">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"> Selecting the Best Sequential Transfer Path for Medical Image Segmentation with Limited Labeled Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jingyun Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingge Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yang 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="2410.06892v1-abstract-short" style="display: inline;"> The medical image processing field often encounters the critical issue of scarce annotated data. Transfer learning has emerged as a solution, yet how to select an adequate source task and effectively transfer the knowledge to the target task remains challenging. To address this, we propose a novel sequential transfer scheme with a task affinity metric tailored for medical images. Considering the c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06892v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06892v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06892v1-abstract-full" style="display: none;"> The medical image processing field often encounters the critical issue of scarce annotated data. Transfer learning has emerged as a solution, yet how to select an adequate source task and effectively transfer the knowledge to the target task remains challenging. To address this, we propose a novel sequential transfer scheme with a task affinity metric tailored for medical images. Considering the characteristics of medical image segmentation tasks, we analyze the image and label similarity between tasks and compute the task affinity scores, which assess the relatedness among tasks. Based on this, we select appropriate source tasks and develop an effective sequential transfer strategy by incorporating intermediate source tasks to gradually narrow the domain discrepancy and minimize the transfer cost. Thereby we identify the best sequential transfer path for the given target task. Extensive experiments on three MRI medical datasets, FeTS 2022, iSeg-2019, and WMH, demonstrate the efficacy of our method in finding the best source sequence. Compared with directly transferring from a single source task, the sequential transfer results underline a significant improvement in target task performance, achieving an average of 2.58% gain in terms of segmentation Dice score, notably, 6.00% for FeTS 2022. Code is available at the git repository. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06892v1-abstract-full').style.display = 'none'; document.getElementById('2410.06892v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06757">arXiv:2410.06757</a> <span> [<a href="https://arxiv.org/pdf/2410.06757">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Diff-FMT: Diffusion Models for Fluorescence Molecular Tomography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xue%2C+Q">Qianqian Xue</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Peng Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xingyu Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wenjian Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guanglei 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="2410.06757v1-abstract-short" style="display: inline;"> Fluorescence molecular tomography (FMT) is a real-time, noninvasive optical imaging technology that plays a significant role in biomedical research. Nevertheless, the ill-posedness of the inverse problem poses huge challenges in FMT reconstructions. Previous various deep learning algorithms have been extensively explored to address the critical issues, but they remain faces the challenge of high d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06757v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06757v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06757v1-abstract-full" style="display: none;"> Fluorescence molecular tomography (FMT) is a real-time, noninvasive optical imaging technology that plays a significant role in biomedical research. Nevertheless, the ill-posedness of the inverse problem poses huge challenges in FMT reconstructions. Previous various deep learning algorithms have been extensively explored to address the critical issues, but they remain faces the challenge of high data dependency with poor image quality. In this paper, we, for the first time, propose a FMT reconstruction method based on a denoising diffusion probabilistic model (DDPM), termed Diff-FMT, which is capable of obtaining high-quality reconstructed images from noisy images. Specifically, we utilize the noise addition mechanism of DDPM to generate diverse training samples. Through the step-by-step probability sampling mechanism in the inverse process, we achieve fine-grained reconstruction of the image, avoiding issues such as loss of image detail that can occur with end-to-end deep-learning methods. Additionally, we introduce the fluorescence signals as conditional information in the model training to sample a reconstructed image that is highly consistent with the input fluorescence signals from the noisy images. Numerous experimental results show that Diff-FMT can achieve high-resolution reconstruction images without relying on large-scale datasets compared with other cutting-edge algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06757v1-abstract-full').style.display = 'none'; document.getElementById('2410.06757v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06555">arXiv:2410.06555</a> <span> [<a href="https://arxiv.org/pdf/2410.06555">pdf</a>, <a href="https://arxiv.org/format/2410.06555">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"> ING-VP: MLLMs cannot Play Easy Vision-based Games Yet </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haoran Zhang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hangyu Guo</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shuyue Guo</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+M">Meng Cao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge 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="2410.06555v1-abstract-short" style="display: inline;"> As multimodal large language models (MLLMs) continue to demonstrate increasingly competitive performance across a broad spectrum of tasks, more intricate and comprehensive benchmarks have been developed to assess these cutting-edge models. These benchmarks introduce new challenges to core capabilities such as perception, reasoning, and planning. However, existing multimodal benchmarks fall short i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06555v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06555v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06555v1-abstract-full" style="display: none;"> As multimodal large language models (MLLMs) continue to demonstrate increasingly competitive performance across a broad spectrum of tasks, more intricate and comprehensive benchmarks have been developed to assess these cutting-edge models. These benchmarks introduce new challenges to core capabilities such as perception, reasoning, and planning. However, existing multimodal benchmarks fall short in providing a focused evaluation of multi-step planning based on spatial relationships in images. To bridge this gap, we present ING-VP, the first INteractive Game-based Vision Planning benchmark, specifically designed to evaluate the spatial imagination and multi-step reasoning abilities of MLLMs. ING-VP features 6 distinct games, encompassing 300 levels, each with 6 unique configurations. A single model engages in over 60,000 rounds of interaction. The benchmark framework allows for multiple comparison settings, including image-text vs. text-only inputs, single-step vs. multi-step reasoning, and with-history vs. without-history conditions, offering valuable insights into the model's capabilities. We evaluated numerous state-of-the-art MLLMs, with the highest-performing model, Claude-3.5 Sonnet, achieving an average accuracy of only 3.37%, far below the anticipated standard. This work aims to provide a specialized evaluation framework to drive advancements in MLLMs' capacity for complex spatial reasoning and planning. The code is publicly available at https://github.com/Thisisus7/ING-VP.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06555v1-abstract-full').style.display = 'none'; document.getElementById('2410.06555v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">49 pages, 12 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06526">arXiv:2410.06526</a> <span> [<a href="https://arxiv.org/pdf/2410.06526">pdf</a>, <a href="https://arxiv.org/format/2410.06526">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+K">Kaijing Ma</a>, <a href="/search/cs?searchtype=author&query=Du%2C+X">Xinrun Du</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yunran Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haoran Zhang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Z">Zhoufutu Wen</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+X">Xingwei Qu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiaheng Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Minghao Liu</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+X">Xiang Yue</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge 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="2410.06526v2-abstract-short" style="display: inline;"> In this paper, we introduce Knowledge-Orthogonal Reasoning (KOR), which minimizes the impact of domain-specific knowledge for a more accurate evaluation of models' reasoning abilities in out-of-distribution scenarios. Based on this concept, we propose the Knowledge-Orthogonal Reasoning Benchmark (KOR-Bench), encompassing five task categories: Operation, Logic, Cipher, Puzzle, and Counterfactual. K… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06526v2-abstract-full').style.display = 'inline'; document.getElementById('2410.06526v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06526v2-abstract-full" style="display: none;"> In this paper, we introduce Knowledge-Orthogonal Reasoning (KOR), which minimizes the impact of domain-specific knowledge for a more accurate evaluation of models' reasoning abilities in out-of-distribution scenarios. Based on this concept, we propose the Knowledge-Orthogonal Reasoning Benchmark (KOR-Bench), encompassing five task categories: Operation, Logic, Cipher, Puzzle, and Counterfactual. KOR-Bench emphasizes the effectiveness of models in applying new rule descriptions to solve novel rule-driven questions. O1-Preview and O1-Mini achieve accuracies of 72.88% and 70.16%, significantly outperforming Claude-3.5-Sonnet and GPT-4o, which score 58.96% and 58.00%, revealing considerable performance gaps and highlighting KOR-Bench's effectiveness. We conduct thorough analyses to identify bottlenecks in the Cipher task using Stepwise Prompting, discovering that two rounds of Self-Correction yield optimal results. Complex Task Processing evaluates model performance across three integrated tasks, while we also explore the impact of Tricks on the Puzzle task and visualize rule-focused attention to enhance our understanding of model behavior. KOR-Bench aims to enhance reasoning evaluation and support further research in this field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06526v2-abstract-full').style.display = 'none'; document.getElementById('2410.06526v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05808">arXiv:2410.05808</a> <span> [<a href="https://arxiv.org/pdf/2410.05808">pdf</a>, <a href="https://arxiv.org/format/2410.05808">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"> Vision Transformer based Random Walk for Group Re-Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guoqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tianqi Liu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+W">Wenxuan Fang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Y">Yuhui Zheng</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="2410.05808v1-abstract-short" style="display: inline;"> Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a no… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05808v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05808v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05808v1-abstract-full" style="display: none;"> Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05808v1-abstract-full').style.display = 'none'; document.getElementById('2410.05808v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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">6 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04810">arXiv:2410.04810</a> <span> [<a href="https://arxiv.org/pdf/2410.04810">pdf</a>, <a href="https://arxiv.org/format/2410.04810">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haokun Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hang Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yao Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Gengyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Bi%2C+J">Jinhe Bi</a>, <a href="/search/cs?searchtype=author&query=Torr%2C+P">Philip Torr</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jindong Gu</a>, <a href="/search/cs?searchtype=author&query=Krompass%2C+D">Denis Krompass</a>, <a href="/search/cs?searchtype=author&query=Tresp%2C+V">Volker Tresp</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="2410.04810v1-abstract-short" style="display: inline;"> One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data or model upload, which reduces communication costs and mitigates privacy threats compared to traditional FL. Despite these promising prospects, existing methods face challenges due to client data heterogeneity and limited… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04810v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04810v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04810v1-abstract-full" style="display: none;"> One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data or model upload, which reduces communication costs and mitigates privacy threats compared to traditional FL. Despite these promising prospects, existing methods face challenges due to client data heterogeneity and limited data quantity when applied to real-world OSFL systems. Recently, Latent Diffusion Models (LDM) have shown remarkable advancements in synthesizing high-quality images through pretraining on large-scale datasets, thereby presenting a potential solution to overcome these issues. However, directly applying pretrained LDM to heterogeneous OSFL results in significant distribution shifts in synthetic data, leading to performance degradation in classification models trained on such data. This issue is particularly pronounced in rare domains, such as medical imaging, which are underrepresented in LDM's pretraining data. To address this challenge, we propose Federated Bi-Level Personalization (FedBiP), which personalizes the pretrained LDM at both instance-level and concept-level. Hereby, FedBiP synthesizes images following the client's local data distribution without compromising the privacy regulations. FedBiP is also the first approach to simultaneously address feature space heterogeneity and client data scarcity in OSFL. Our method is validated through extensive experiments on three OSFL benchmarks with feature space heterogeneity, as well as on challenging medical and satellite image datasets with label heterogeneity. The results demonstrate the effectiveness of FedBiP, which substantially outperforms other OSFL methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04810v1-abstract-full').style.display = 'none'; document.getElementById('2410.04810v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 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/2410.04354">arXiv:2410.04354</a> <span> [<a href="https://arxiv.org/pdf/2410.04354">pdf</a>, <a href="https://arxiv.org/format/2410.04354">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"> StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cui%2C+X">Xiao Cui</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+W">Weicai Ye</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guofeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wengang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Houqiang 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="2410.04354v2-abstract-short" style="display: inline;"> Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object relationships, and data sparsity across multiple scales. Despite recent advancements, existing surface reconstruction methods, which are primarily designed for object-centr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04354v2-abstract-full').style.display = 'inline'; document.getElementById('2410.04354v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04354v2-abstract-full" style="display: none;"> Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object relationships, and data sparsity across multiple scales. Despite recent advancements, existing surface reconstruction methods, which are primarily designed for object-centric scenarios, struggle to adapt effectively to the unique characteristics of street scenes. To address this challenge, we introduce StreetSurfGS, the first method to employ Gaussian Splatting specifically tailored for scalable urban street scene surface reconstruction. StreetSurfGS utilizes a planar-based octree representation and segmented training to reduce memory costs, accommodate unique camera characteristics, and ensure scalability. Additionally, to mitigate depth inaccuracies caused by object overlap, we propose a guided smoothing strategy within regularization to eliminate inaccurate boundary points and outliers. Furthermore, to address sparse views and multi-scale challenges, we use a dual-step matching strategy that leverages adjacent and long-term information. Extensive experiments validate the efficacy of StreetSurfGS in both novel view synthesis and surface reconstruction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04354v2-abstract-full').style.display = 'none'; document.getElementById('2410.04354v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03765">arXiv:2410.03765</a> <span> [<a href="https://arxiv.org/pdf/2410.03765">pdf</a>, <a href="https://arxiv.org/format/2410.03765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingcun Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yu-Guang Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+I">Ing-Chao Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G+L">Grace Li 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="2410.03765v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have achieved remarkable breakthroughs. However, the huge number of parameters in LLMs require significant amount of memory storage in inference, which prevents their practical deployment in many applications. To reduce memory storage of LLMs, singular value decomposition (SVD) provides a promising solution to approximate weight matrices for compressing LLMs. In this p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03765v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03765v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03765v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have achieved remarkable breakthroughs. However, the huge number of parameters in LLMs require significant amount of memory storage in inference, which prevents their practical deployment in many applications. To reduce memory storage of LLMs, singular value decomposition (SVD) provides a promising solution to approximate weight matrices for compressing LLMs. In this paper, we take a step further to explore parameter sharing across different layers with SVD to achieve more effective compression for LLMs. Specifically, weight matrices in different layers are decomposed and represented as a linear combination of a set of shared basis vectors and unique coefficients. The types of weight matrices and the layer selection for basis sharing are examined when compressing LLMs to maintain the performance. Comprehensive experiments demonstrate that Basis Sharing outperforms state-of-the-art SVD-based compression approaches and parameter sharing techniques, especially under large compression ratios. Code is available at: https://github.com/TUDa-HWAI/Basis_Sharing <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03765v1-abstract-full').style.display = 'none'; document.getElementById('2410.03765v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03751">arXiv:2410.03751</a> <span> [<a href="https://arxiv.org/pdf/2410.03751">pdf</a>, <a href="https://arxiv.org/format/2410.03751">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"> Recent Advances in Speech Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cui%2C+W">Wenqian Cui</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Dianzhi Yu</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+X">Xiaoqi Jiao</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+Z">Ziqiao Meng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Guangyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qichao Wang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Yiwen Guo</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</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="2410.03751v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightforward approach to achieve this involves a pipeline of ``Automatic Speech Recognition (ASR) + LLM + Text-to-Speech (TTS)", where input speech is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03751v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03751v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03751v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightforward approach to achieve this involves a pipeline of ``Automatic Speech Recognition (ASR) + LLM + Text-to-Speech (TTS)", where input speech is transcribed to text, processed by an LLM, and then converted back to speech. Despite being straightforward, this method suffers from inherent limitations, such as information loss during modality conversion and error accumulation across the three stages. To address these issues, Speech Language Models (SpeechLMs) -- end-to-end models that generate speech without converting from text -- have emerged as a promising alternative. This survey paper provides the first comprehensive overview of recent methodologies for constructing SpeechLMs, detailing the key components of their architecture and the various training recipes integral to their development. Additionally, we systematically survey the various capabilities of SpeechLMs, categorize the evaluation metrics for SpeechLMs, and discuss the challenges and future research directions in this rapidly evolving field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03751v1-abstract-full').style.display = 'none'; document.getElementById('2410.03751v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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=Zhang%2C+G&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+G&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