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 647 results for author: <span class="mathjax">Fang, Y</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Fang%2C+Y">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Fang, Y"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Fang%2C+Y&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Fang, Y"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.15558">arXiv:2411.15558</a> <span> [<a href="https://arxiv.org/pdf/2411.15558">pdf</a>, <a href="https://arxiv.org/format/2411.15558">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> </div> </div> <p class="title is-5 mathjax"> Reassessing Layer Pruning in LLMs: New Insights and Methods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yao Lu</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+H">Hao Cheng</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yujie Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zeyu Wang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+J">Jiaheng Wei</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Dongwei Xu</a>, <a href="/search/cs?searchtype=author&query=Xuan%2C+Q">Qi Xuan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaoniu Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhaowei Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.15558v1-abstract-short" style="display: inline;"> Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained environments. Layer pruning, as a simple yet effective compression method, removes layers of a model directly, reducing computational overhead. However, what are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15558v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15558v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15558v1-abstract-full" style="display: none;"> Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained environments. Layer pruning, as a simple yet effective compression method, removes layers of a model directly, reducing computational overhead. However, what are the best practices for layer pruning in LLMs? Are sophisticated layer selection metrics truly effective? Does the LoRA (Low-Rank Approximation) family, widely regarded as a leading method for pruned model fine-tuning, truly meet expectations when applied to post-pruning fine-tuning? To answer these questions, we dedicate thousands of GPU hours to benchmarking layer pruning in LLMs and gaining insights across multiple dimensions. Our results demonstrate that a simple approach, i.e., pruning the final 25\% of layers followed by fine-tuning the \texttt{lm\_head} and the remaining last three layer, yields remarkably strong performance. Following this guide, we prune Llama-3.1-8B-It and obtain a model that outperforms many popular LLMs of similar size, such as ChatGLM2-6B, Vicuna-7B-v1.5, Qwen1.5-7B and Baichuan2-7B. We release the optimal model weights on Huggingface, and the code is available on GitHub. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15558v1-abstract-full').style.display = 'none'; document.getElementById('2411.15558v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 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/2411.12980">arXiv:2411.12980</a> <span> [<a href="https://arxiv.org/pdf/2411.12980">pdf</a>, <a href="https://arxiv.org/format/2411.12980">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"> LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiao%2C+S">Siwen Jiao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yangyi Fang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+B">Baoyun Peng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wangqun Chen</a>, <a href="/search/cs?searchtype=author&query=Veeravalli%2C+B">Bharadwaj Veeravalli</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="2411.12980v2-abstract-short" style="display: inline;"> Recent advancements in Visual Language Models (VLMs) have made them crucial for visual question answering (VQA) in autonomous driving, enabling natural human-vehicle interactions. However, existing methods often struggle in dynamic driving environments, as they usually focus on static images or videos and rely on downsampling to manage computational costs. This results in the loss of critical deta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12980v2-abstract-full').style.display = 'inline'; document.getElementById('2411.12980v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12980v2-abstract-full" style="display: none;"> Recent advancements in Visual Language Models (VLMs) have made them crucial for visual question answering (VQA) in autonomous driving, enabling natural human-vehicle interactions. However, existing methods often struggle in dynamic driving environments, as they usually focus on static images or videos and rely on downsampling to manage computational costs. This results in the loss of critical details and the difficulty in effectively integrating spatial and temporal information, undermining fine-grained perception and temporal coherence essential for effective decision-making. To tackle these challenges, we introduce LaVida Drive, a novel and efficient VQA framework for autonomous driving. LaVida Drive seamlessly integrates temporal data while maintaining high-resolution inputs for detailed visual perception. It optimizes spatial processing by retaining high-resolution data for intricate details and using lower-resolution inputs for temporal analysis to focus on motion-related features, thereby boosting computational efficiency. The core of LaVida Drive consists of two modules: the \textit{Query-aware Token Selection} module and the \textit{Spatial-Temporal Token Recovery and Enhancement} module. The former dynamically selects the most relevant visual tokens based on semantic alignment with the input query, reducing the token count from high-resolution spatial input. The latter ensures smooth and coherent interactions between spatial and temporal information, preserving contextual continuity across frames. Extensive experiments on various autonomous driving question-answering benchmarks show that LaVida Drive significantly reduces visual tokens, enhances efficiency, and improves overall performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12980v2-abstract-full').style.display = 'none'; document.getElementById('2411.12980v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11304">arXiv:2411.11304</a> <span> [<a href="https://arxiv.org/pdf/2411.11304">pdf</a>, <a href="https://arxiv.org/format/2411.11304">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"> Toward Personalized Federated Node Classification in One-shot Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+G">Guochen Yan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xunkai Li</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+L">Luyuan Xie</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wentao Zhang</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Q">Qingni Shen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuejian Fang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhonghai Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11304v2-abstract-short" style="display: inline;"> Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos in distributed private graphs data management. In practical scenarios involving complex and heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL) aims to enhance model utility by training personalized models tailored to individual client needs, rather than relying on a universal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11304v2-abstract-full').style.display = 'inline'; document.getElementById('2411.11304v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11304v2-abstract-full" style="display: none;"> Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos in distributed private graphs data management. In practical scenarios involving complex and heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL) aims to enhance model utility by training personalized models tailored to individual client needs, rather than relying on a universal global model. However, existing pFGL methods often require numerous communication rounds under heterogeneous client graphs, leading to significant security concerns and communication overhead. While One-shot Federated Learning (OFL) addresses these issues by enabling collaboration in a single round, existing OFL methods are designed for image-based tasks and ineffective for graph data, leaving a critical gap in the field. Additionally, personalized models often suffer from bias, failing to generalize effectively to minority data. To address these challenges, we propose the first one-shot personalized federated graph learning method for node classification, compatible with the Secure Aggregation protocol for privacy preservation. Specifically, for effective graph learning in a single communication round, our method estimates and aggregates class-wise feature distribution statistics to construct a global pseudo-graph on the server, facilitating the training of a global graph model. Moreover, to mitigate bias, we introduce a two-stage personalized training approach that adaptively balances local personal information and global insights from the pseudo-graph, improving both personalization and generalization. Extensive experiments conducted on 8 multi-scale graph datasets demonstrate that our method significantly outperforms state-of-the-art baselines across various settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11304v2-abstract-full').style.display = 'none'; document.getElementById('2411.11304v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10028">arXiv:2411.10028</a> <span> [<a href="https://arxiv.org/pdf/2411.10028">pdf</a>, <a href="https://arxiv.org/format/2411.10028">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"> MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yanzhao Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10028v2-abstract-short" style="display: inline;"> The goal of multi-object tracking (MOT) is to detect and track all objects in a scene across frames, while maintaining a unique identity for each object. Most existing methods rely on the spatial-temporal motion features and appearance embedding features of the detected objects in consecutive frames. Effectively and robustly representing the spatial and appearance features of long trajectories has… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10028v2-abstract-full').style.display = 'inline'; document.getElementById('2411.10028v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10028v2-abstract-full" style="display: none;"> The goal of multi-object tracking (MOT) is to detect and track all objects in a scene across frames, while maintaining a unique identity for each object. Most existing methods rely on the spatial-temporal motion features and appearance embedding features of the detected objects in consecutive frames. Effectively and robustly representing the spatial and appearance features of long trajectories has become a critical factor affecting the performance of MOT. We propose a novel approach for appearance and spatial-temporal motion feature representation, improving upon the hierarchical clustering association method MOT FCG. For spatialtemporal motion features, we first propose Diagonal Modulated GIoU, which more accurately represents the relationship between the position and shape of the objects. Second, Mean Constant Velocity Modeling is proposed to reduce the effect of observation noise on target motion state estimation. For appearance features, we utilize a dynamic appearance representation that incorporates confidence information, enabling the trajectory appearance features to be more robust and global. Based on the baseline model MOT FCG, we have realized further improvements in the performance of all. we achieved 63.1 HOTA, 76.9 MOTA and 78.2 IDF1 on the MOT17 test set, and also achieved competitive performance on the MOT20 and DanceTrack sets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10028v2-abstract-full').style.display = 'none'; document.getElementById('2411.10028v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 7 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/2411.09593">arXiv:2411.09593</a> <span> [<a href="https://arxiv.org/pdf/2411.09593">pdf</a>, <a href="https://arxiv.org/format/2411.09593">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="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"> SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Soumick Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Mattern%2C+H">Hendrik Mattern</a>, <a href="/search/cs?searchtype=author&query=D%C3%B6rner%2C+M">Marc D枚rner</a>, <a href="/search/cs?searchtype=author&query=Sciarra%2C+A">Alessandro Sciarra</a>, <a href="/search/cs?searchtype=author&query=Dubost%2C+F">Florian Dubost</a>, <a href="/search/cs?searchtype=author&query=Schnurre%2C+H">Hannes Schnurre</a>, <a href="/search/cs?searchtype=author&query=Khatun%2C+R">Rupali Khatun</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+C">Chun-Chih Yu</a>, <a href="/search/cs?searchtype=author&query=Hsieh%2C+T">Tsung-Lin Hsieh</a>, <a href="/search/cs?searchtype=author&query=Tsai%2C+Y">Yi-Shan Tsai</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi-Zeng Fang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yung-Ching Yang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Juinn-Dar Huang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Marshall Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Siyu Liu</a>, <a href="/search/cs?searchtype=author&query=Ribeiro%2C+F+L">Fernanda L. Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Bollmann%2C+S">Saskia Bollmann</a>, <a href="/search/cs?searchtype=author&query=Chintalapati%2C+K+V">Karthikesh Varma Chintalapati</a>, <a href="/search/cs?searchtype=author&query=Radhakrishna%2C+C+M">Chethan Mysuru Radhakrishna</a>, <a href="/search/cs?searchtype=author&query=Kumara%2C+S+C+H+R">Sri Chandana Hudukula Ram Kumara</a>, <a href="/search/cs?searchtype=author&query=Sutrave%2C+R">Raviteja Sutrave</a>, <a href="/search/cs?searchtype=author&query=Qayyum%2C+A">Abdul Qayyum</a>, <a href="/search/cs?searchtype=author&query=Mazher%2C+M">Moona Mazher</a>, <a href="/search/cs?searchtype=author&query=Razzak%2C+I">Imran Razzak</a>, <a href="/search/cs?searchtype=author&query=Rodero%2C+C">Cristobal Rodero</a> , et al. (23 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="2411.09593v1-abstract-short" style="display: inline;"> The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, maki… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09593v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09593v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09593v1-abstract-full" style="display: none;"> The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, making it possible to visualise such vessels in the brain. However, the lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. To address this, the SMILE-UHURA challenge was organised. This challenge, held in conjunction with the ISBI 2023, in Cartagena de Indias, Colombia, aimed to provide a platform for researchers working on related topics. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. This dataset was created through a combination of automated pre-segmentation and extensive manual refinement. In this manuscript, sixteen submitted methods and two baseline methods are compared both quantitatively and qualitatively on two different datasets: held-out test MRAs from the same dataset as the training data (with labels kept secret) and a separate 7T ToF MRA dataset where both input volumes and labels are kept secret. The results demonstrate that most of the submitted deep learning methods, trained on the provided training dataset, achieved reliable segmentation performance. Dice scores reached up to 0.838 $\pm$ 0.066 and 0.716 $\pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $\pm$ 0.15. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09593v1-abstract-full').style.display = 'none'; document.getElementById('2411.09593v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06102">arXiv:2411.06102</a> <span> [<a href="https://arxiv.org/pdf/2411.06102">pdf</a>, <a href="https://arxiv.org/format/2411.06102">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"> SiriusBI: Building End-to-End Business Intelligence Enhanced by Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jie Jiang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+H">Haining Xie</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yu Shen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zihan Zhang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+M">Meng Lei</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Y">Yifeng Zheng</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yide Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunyou Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+D">Danqing Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wentao Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaofeng Yang</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+B">Bin Cui</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Peng 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="2411.06102v1-abstract-short" style="display: inline;"> The rapid advancement of AI technologies, particularly Large Language Models (LLMs), is establishing a new paradigm for Business Intelligence (BI). Despite the emergence of pioneering work in enhancing BI systems with LLMs, we have identified the following three issues when deployed in real industrial scenarios: interaction limitations, performance bottlenecks, and functionality deficiencies. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06102v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06102v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06102v1-abstract-full" style="display: none;"> The rapid advancement of AI technologies, particularly Large Language Models (LLMs), is establishing a new paradigm for Business Intelligence (BI). Despite the emergence of pioneering work in enhancing BI systems with LLMs, we have identified the following three issues when deployed in real industrial scenarios: interaction limitations, performance bottlenecks, and functionality deficiencies. In this paper, we present SiriusBI, an end-to-end business intelligence system that is designed to address the three issues simultaneously. First, we propose an intelligent and application-oriented module called multi-round dialogue with querying, which aims to overcome the prevalent interaction limitations in current BI solutions. Next, to mitigate the performance bottlenecks caused by scenario migration, we introduce two SQL generation methods that strike a balance between accuracy and deployment costs. Finally, to tackle the practical challenges posed by functionality deficiencies, we develop an end-to-end workflow that covers the entire BI process, ensuring that SiriusBI delivers a robust and complete set of functionalities. As an independent cloud service in Tencent's data platform, SiriusBI has been applied across Tencent's finance, advertising, and cloud sectors, providing services to dozens of enterprise clients. Experiments on real-world datasets and practical applications in industrial BI scenarios demonstrate the practicality and effectiveness of SiriusBI. Remarkably, SiriusBI achieves remarkable accuracy rates of 97% in SQL generation for Tencent Finance, 89% for Tencent Advertisement, and 91% for Tencent Cloud. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06102v1-abstract-full').style.display = 'none'; document.getElementById('2411.06102v1-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">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, 5figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05261">arXiv:2411.05261</a> <span> [<a href="https://arxiv.org/pdf/2411.05261">pdf</a>, <a href="https://arxiv.org/format/2411.05261">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Decoding Report Generators: A Cyclic Vision-Language Adapter for Counterfactual Explanations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yingying Fang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Z">Zihao Jin</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shaojie Guo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinda Liu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yijian Gao</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+J">Junzhi Ning</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+Z">Zhiling Yue</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhi Li</a>, <a href="/search/cs?searchtype=author&query=Walsh%2C+S+L">Simon LF Walsh</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05261v1-abstract-short" style="display: inline;"> Despite significant advancements in report generation methods, a critical limitation remains: the lack of interpretability in the generated text. This paper introduces an innovative approach to enhance the explainability of text generated by report generation models. Our method employs cyclic text manipulation and visual comparison to identify and elucidate the features in the original content tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05261v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05261v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05261v1-abstract-full" style="display: none;"> Despite significant advancements in report generation methods, a critical limitation remains: the lack of interpretability in the generated text. This paper introduces an innovative approach to enhance the explainability of text generated by report generation models. Our method employs cyclic text manipulation and visual comparison to identify and elucidate the features in the original content that influence the generated text. By manipulating the generated reports and producing corresponding images, we create a comparative framework that highlights key attributes and their impact on the text generation process. This approach not only identifies the image features aligned to the generated text but also improves transparency but also provides deeper insights into the decision-making mechanisms of the report generation models. Our findings demonstrate the potential of this method to significantly enhance the interpretability and transparency of AI-generated reports. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05261v1-abstract-full').style.display = 'none'; document.getElementById('2411.05261v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03551">arXiv:2411.03551</a> <span> [<a href="https://arxiv.org/pdf/2411.03551">pdf</a>, <a href="https://arxiv.org/format/2411.03551">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="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"> Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yue%2C+Z">Zhiling Yue</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yingying Fang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Liutao Yang</a>, <a href="/search/cs?searchtype=author&query=Baid%2C+N">Nikhil Baid</a>, <a href="/search/cs?searchtype=author&query=Walsh%2C+S">Simon Walsh</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03551v1-abstract-short" style="display: inline;"> Fibrotic Lung Disease (FLD) is a severe condition marked by lung stiffening and scarring, leading to respiratory decline. High-resolution computed tomography (HRCT) is critical for diagnosing and monitoring FLD; however, fibrosis appears as irregular, diffuse patterns with unclear boundaries, leading to high inter-observer variability and time-intensive manual annotation. To tackle this challenge,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03551v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03551v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03551v1-abstract-full" style="display: none;"> Fibrotic Lung Disease (FLD) is a severe condition marked by lung stiffening and scarring, leading to respiratory decline. High-resolution computed tomography (HRCT) is critical for diagnosing and monitoring FLD; however, fibrosis appears as irregular, diffuse patterns with unclear boundaries, leading to high inter-observer variability and time-intensive manual annotation. To tackle this challenge, we propose DiffSeg, a novel weakly supervised semantic segmentation (WSSS) method that uses image-level annotations to generate pixel-level fibrosis segmentation, reducing the need for fine-grained manual labeling. Additionally, our DiffSeg incorporates a diffusion-based generative model to synthesize HRCT images with different levels of fibrosis from healthy slices, enabling the generation of the fibrosis-injected slices and their paired fibrosis location. Experiments indicate that our method significantly improves the accuracy of pseudo masks generated by existing WSSS methods, greatly reducing the complexity of manual labeling and enhancing the consistency of the generated masks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03551v1-abstract-full').style.display = 'none'; document.getElementById('2411.03551v1-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">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/2411.00888">arXiv:2411.00888</a> <span> [<a href="https://arxiv.org/pdf/2411.00888">pdf</a>, <a href="https://arxiv.org/format/2411.00888">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> <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="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qianqian Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wei Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuqi Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hong-Jun Li</a>, <a href="/search/cs?searchtype=author&query=Bozoki%2C+A">Andrea Bozoki</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mingxia 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="2411.00888v1-abstract-short" style="display: inline;"> Brain networks/graphs derived from resting-state functional MRI (fMRI) help study underlying pathophysiology of neurocognitive disorders by measuring neuronal activities in the brain. Some studies utilize learning-based methods for brain network analysis, but typically suffer from low model generalizability caused by scarce labeled fMRI data. As a notable self-supervised strategy, graph contrastiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00888v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00888v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00888v1-abstract-full" style="display: none;"> Brain networks/graphs derived from resting-state functional MRI (fMRI) help study underlying pathophysiology of neurocognitive disorders by measuring neuronal activities in the brain. Some studies utilize learning-based methods for brain network analysis, but typically suffer from low model generalizability caused by scarce labeled fMRI data. As a notable self-supervised strategy, graph contrastive learning helps leverage auxiliary unlabeled data. But existing methods generally arbitrarily perturb graph nodes/edges to generate augmented graphs, without considering essential topology information of brain networks. To this end, we propose a topology-aware graph augmentation (TGA) framework, comprising a pretext model to train a generalizable encoder on large-scale unlabeled fMRI cohorts and a task-specific model to perform downstream tasks on a small target dataset. In the pretext model, we design two novel topology-aware graph augmentation strategies: (1) hub-preserving node dropping that prioritizes preserving brain hub regions according to node importance, and (2) weight-dependent edge removing that focuses on keeping important functional connectivities based on edge weights. Experiments on 1, 688 fMRI scans suggest that TGA outperforms several state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00888v1-abstract-full').style.display = 'none'; document.getElementById('2411.00888v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00437">arXiv:2411.00437</a> <span> [<a href="https://arxiv.org/pdf/2411.00437">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yun Jiang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Z">Zilong Xie</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yun Fang</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+S">Shuai Pan</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="2411.00437v1-abstract-short" style="display: inline;"> Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models. In this paper, we propose an end-to-end model with adaptive filtering for retrieval-augmented generation (E2E-AFG), which integrates answer existe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00437v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00437v1-abstract-full" style="display: none;"> Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models. In this paper, we propose an end-to-end model with adaptive filtering for retrieval-augmented generation (E2E-AFG), which integrates answer existence judgment and text generation into a single end-to-end framework. This enables the model to focus more effectively on relevant content while reducing the influence of irrelevant information and generating accurate answers. We evaluate E2E-AFG on six representative knowledge-intensive language datasets, and the results show that it consistently outperforms baseline models across all tasks, demonstrating the effectiveness and robustness of the proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00437v1-abstract-full').style.display = 'none'; document.getElementById('2411.00437v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 3 figures, 5 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/2410.23978">arXiv:2410.23978</a> <span> [<a href="https://arxiv.org/pdf/2410.23978">pdf</a>, <a href="https://arxiv.org/format/2410.23978">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuaihang Yuan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao Huang</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yu Hao</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+C">Congcong Wen</a>, <a href="/search/cs?searchtype=author&query=Tzes%2C+A">Anthony Tzes</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23978v1-abstract-short" style="display: inline;"> Zero-Shot Object Goal Navigation (ZS-OGN) enables robots or agents to navigate toward objects of unseen categories without object-specific training. Traditional approaches often leverage categorical semantic information for navigation guidance, which struggles when only objects are partially observed or detailed and functional representations of the environment are lacking. To resolve the above tw… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23978v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23978v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23978v1-abstract-full" style="display: none;"> Zero-Shot Object Goal Navigation (ZS-OGN) enables robots or agents to navigate toward objects of unseen categories without object-specific training. Traditional approaches often leverage categorical semantic information for navigation guidance, which struggles when only objects are partially observed or detailed and functional representations of the environment are lacking. To resolve the above two issues, we propose \textit{Geometric-part and Affordance Maps} (GAMap), a novel method that integrates object parts and affordance attributes as navigation guidance. Our method includes a multi-scale scoring approach to capture geometric-part and affordance attributes of objects at different scales. Comprehensive experiments conducted on HM3D and Gibson benchmark datasets demonstrate improvements in Success Rate and Success weighted by Path Length, underscoring the efficacy of our geometric-part and affordance-guided navigation approach in enhancing robot autonomy and versatility, without any additional object-specific training or fine-tuning with the semantics of unseen objects and/or the locomotions of the robot. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23978v1-abstract-full').style.display = 'none'; document.getElementById('2410.23978v1-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">16 pages, 8 figures, 7 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/2410.23855">arXiv:2410.23855</a> <span> [<a href="https://arxiv.org/pdf/2410.23855">pdf</a>, <a href="https://arxiv.org/format/2410.23855">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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> RAGraph: A General Retrieval-Augmented Graph Learning Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xinke Jiang</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+R">Rihong Qiu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yongxin Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wentao Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yichen Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruizhe Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuchen Fang</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+X">Xu Chu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Junfeng Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yasha 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="2410.23855v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGraph), which brings external graph data into the general graph foundation model to imp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23855v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23855v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23855v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGraph), which brings external graph data into the general graph foundation model to improve model generalization on unseen scenarios. On the top of our framework is a toy graph vector library that we established, which captures key attributes, such as features and task-specific label information. During inference, the RAGraph adeptly retrieves similar toy graphs based on key similarities in downstream tasks, integrating the retrieved data to enrich the learning context via the message-passing prompting mechanism. Our extensive experimental evaluations demonstrate that RAGraph significantly outperforms state-of-the-art graph learning methods in multiple tasks such as node classification, link prediction, and graph classification across both dynamic and static datasets. Furthermore, extensive testing confirms that RAGraph consistently maintains high performance without the need for task-specific fine-tuning, highlighting its adaptability, robustness, and broad applicability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23855v1-abstract-full').style.display = 'none'; document.getElementById('2410.23855v1-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">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/2410.21926">arXiv:2410.21926</a> <span> [<a href="https://arxiv.org/pdf/2410.21926">pdf</a>, <a href="https://arxiv.org/format/2410.21926">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Unlu%2C+H+U">Halil Utku Unlu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuaihang Yuan</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+C">Congcong Wen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao Huang</a>, <a href="/search/cs?searchtype=author&query=Tzes%2C+A">Anthony Tzes</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21926v1-abstract-short" style="display: inline;"> We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an Instr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21926v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21926v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21926v1-abstract-full" style="display: none;"> We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an InstructionBLIP model for validation. This combination not only refines object and environmental recognition but also fortifies the semantic interpretation, pivotal for navigational decision-making. Our method, rigorously tested in both simulated and real-world settings, exhibits marked improvements in navigation precision and reliability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21926v1-abstract-full').style.display = 'none'; document.getElementById('2410.21926v1-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">16 pages, 7 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/2410.21037">arXiv:2410.21037</a> <span> [<a href="https://arxiv.org/pdf/2410.21037">pdf</a>, <a href="https://arxiv.org/format/2410.21037">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuaihang Yuan</a>, <a href="/search/cs?searchtype=author&query=Unlu%2C+H+U">Halil Utku Unlu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao Huang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+C">Congcong Wen</a>, <a href="/search/cs?searchtype=author&query=Tzes%2C+A">Anthony Tzes</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21037v1-abstract-short" style="display: inline;"> In this paper, we present a novel method for reliable frontier selection in Zero-Shot Object Goal Navigation (ZS-OGN), enhancing robotic navigation systems with foundation models to improve commonsense reasoning in indoor environments. Our approach introduces a multi-expert decision framework to address the nonsensical or irrelevant reasoning often seen in foundation model-based systems. The metho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21037v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21037v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21037v1-abstract-full" style="display: none;"> In this paper, we present a novel method for reliable frontier selection in Zero-Shot Object Goal Navigation (ZS-OGN), enhancing robotic navigation systems with foundation models to improve commonsense reasoning in indoor environments. Our approach introduces a multi-expert decision framework to address the nonsensical or irrelevant reasoning often seen in foundation model-based systems. The method comprises two key components: Diversified Expert Frontier Analysis (DEFA) and Consensus Decision Making (CDM). DEFA utilizes three expert models: furniture arrangement, room type analysis, and visual scene reasoning, while CDM aggregates their outputs, prioritizing unanimous or majority consensus for more reliable decisions. Demonstrating state-of-the-art performance on the RoboTHOR and HM3D datasets, our method excels at navigating towards untrained objects or goals and outperforms various baselines, showcasing its adaptability to dynamic real-world conditions and superior generalization capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21037v1-abstract-full').style.display = 'none'; document.getElementById('2410.21037v1-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">17 pages, 5 figures, 3 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/2410.19777">arXiv:2410.19777</a> <span> [<a href="https://arxiv.org/pdf/2410.19777">pdf</a>, <a href="https://arxiv.org/format/2410.19777">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning-driven Mobile Traffic Measurement Collection and Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yini Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19777v1-abstract-short" style="display: inline;"> Modelling dynamic traffic patterns and especially the continuously changing dependencies between different base stations, which previous studies overlook, is challenging. Traditional algorithms struggle to process large volumes of data and to extract deep insights that help elucidate mobile traffic demands with fine granularity, as well as how these demands will evolve in the future. Therefore, in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19777v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19777v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19777v1-abstract-full" style="display: none;"> Modelling dynamic traffic patterns and especially the continuously changing dependencies between different base stations, which previous studies overlook, is challenging. Traditional algorithms struggle to process large volumes of data and to extract deep insights that help elucidate mobile traffic demands with fine granularity, as well as how these demands will evolve in the future. Therefore, in this thesis we harness the powerful hierarchical feature learning abilities of Deep Learning (DL) techniques in both spatial and temporal domains and develop solutions for precise city-scale mobile traffic analysis and forecasting. Firstly, we design Spider, a mobile traffic measurement collection and reconstruction framework with a view to reducing the cost of measurement collection and inferring traffic consumption with high accuracy, despite working with sparse information. In particular, we train a reinforcement learning agent to selectively sample subsets of target mobile coverage areas and tackle the large action space problem specific to this setting. We then introduce a lightweight neural network model to reconstruct the traffic consumption based on historical sparse measurements. Our proposed framework outperforms existing solutions on a real-world mobile traffic dataset. Secondly, we design SDGNet, a handover-aware graph neural network model for long-term mobile traffic forecasting. We model the cellular network as a graph, and leverage handover frequency to capture the dependencies between base stations across time. Handover information reflects user mobility such as daily commute, which helps in increasing the accuracy of the forecasts made. We proposed dynamic graph convolution to extract features from both traffic consumption and handover data, showing that our model outperforms other benchmark graph models on a mobile traffic dataset collected by a major network operator. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19777v1-abstract-full').style.display = 'none'; document.getElementById('2410.19777v1-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">MPhil thesis</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18852">arXiv:2410.18852</a> <span> [<a href="https://arxiv.org/pdf/2410.18852">pdf</a>, <a href="https://arxiv.org/format/2410.18852">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Geometry">cs.CG</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="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> DL-Polycube: Deep learning enhanced polycube method for high-quality hexahedral mesh generation and volumetric spline construction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yuxuan Yu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuzhuo Fang</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+H">Hua Tong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y+J">Yongjie Jessica 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="2410.18852v1-abstract-short" style="display: inline;"> In this paper, we present a novel algorithm that integrates deep learning with the polycube method (DL-Polycube) to generate high-quality hexahedral (hex) meshes, which are then used to construct volumetric splines for isogeometric analysis. Our DL-Polycube algorithm begins by establishing a connection between surface triangular meshes and polycube structures. We employ deep neural network to clas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18852v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18852v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18852v1-abstract-full" style="display: none;"> In this paper, we present a novel algorithm that integrates deep learning with the polycube method (DL-Polycube) to generate high-quality hexahedral (hex) meshes, which are then used to construct volumetric splines for isogeometric analysis. Our DL-Polycube algorithm begins by establishing a connection between surface triangular meshes and polycube structures. We employ deep neural network to classify surface triangular meshes into their corresponding polycube structures. Following this, we combine the acquired polycube structural information with unsupervised learning to perform surface segmentation of triangular meshes. This step addresses the issue of segmentation not corresponding to a polycube while reducing manual intervention. Quality hex meshes are then generated from the polycube structures, with employing octree subdivision, parametric mapping and quality improvement techniques. The incorporation of deep learning for creating polycube structures, combined with unsupervised learning for segmentation of surface triangular meshes, substantially accelerates hex mesh generation. Finally, truncated hierarchical B-splines are constructed on the generated hex meshes. We extract trivariate B茅zier elements from these splines and apply them directly in isogeometric analysis. We offer several examples to demonstrate the robustness of our DL-Polycube algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18852v1-abstract-full').style.display = 'none'; document.getElementById('2410.18852v1-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/2410.18570">arXiv:2410.18570</a> <span> [<a href="https://arxiv.org/pdf/2410.18570">pdf</a>, <a href="https://arxiv.org/format/2410.18570">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Zero-shot Object Navigation with Vision-Language Models Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wen%2C+C">Congcong Wen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yisiyuan Huang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao Huang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yanjia Huang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuaihang Yuan</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yu Hao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hui Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yu-Shen Liu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18570v1-abstract-short" style="display: inline;"> Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data. Language-driven zero-shot object navigation (L-ZSON) is an extension of ZSON that incorporates natural… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18570v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18570v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18570v1-abstract-full" style="display: none;"> Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data. Language-driven zero-shot object navigation (L-ZSON) is an extension of ZSON that incorporates natural language instructions to guide robot navigation and interaction with objects. In this paper, we propose a novel Vision Language model with a Tree-of-thought Network (VLTNet) for L-ZSON. VLTNet comprises four main modules: vision language model understanding, semantic mapping, tree-of-thought reasoning and exploration, and goal identification. Among these modules, Tree-of-Thought (ToT) reasoning and exploration module serves as a core component, innovatively using the ToT reasoning framework for navigation frontier selection during robot exploration. Compared to conventional frontier selection without reasoning, navigation using ToT reasoning involves multi-path reasoning processes and backtracking when necessary, enabling globally informed decision-making with higher accuracy. Experimental results on PASTURE and RoboTHOR benchmarks demonstrate the outstanding performance of our model in LZSON, particularly in scenarios involving complex natural language as target instructions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18570v1-abstract-full').style.display = 'none'; document.getElementById('2410.18570v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the International Conference on Pattern Recognition (ICPR) for Oral presentation</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15060">arXiv:2410.15060</a> <span> [<a href="https://arxiv.org/pdf/2410.15060">pdf</a>, <a href="https://arxiv.org/format/2410.15060">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"> BYOCL: Build Your Own Consistent Latent with Hierarchical Representative Latent Clustering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dai%2C+J">Jiayue Dai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yunya Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yihan Fang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuetong Chen</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+B">Butian Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15060v1-abstract-short" style="display: inline;"> To address the semantic inconsistency issue with SAM or other single-image segmentation models handling image sequences, we introduce BYOCL. This novel model outperforms SAM in extensive experiments, showcasing its Hierarchical prototype capabilities across CLIP and other representations. BYOCL significantly reduces time and space consumption by dividing inputs into smaller batches, achieving expo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15060v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15060v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15060v1-abstract-full" style="display: none;"> To address the semantic inconsistency issue with SAM or other single-image segmentation models handling image sequences, we introduce BYOCL. This novel model outperforms SAM in extensive experiments, showcasing its Hierarchical prototype capabilities across CLIP and other representations. BYOCL significantly reduces time and space consumption by dividing inputs into smaller batches, achieving exponential time reduction compared to previous methods. Our approach leverages the SAM image encoder for feature extraction, followed by Intra-Batch and Inter-Batch clustering algorithms. Extensive experiments demonstrate that BYOCL far exceeds the previous state-of-the-art single image segmentation model. Our work is the first to apply consistent segmentation using foundation models without requiring training, utilizing plug-and-play modules for any latent space, making our method highly efficientModels are available at \href{https://github.com/cyt1202/BYOCL.git <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15060v1-abstract-full').style.display = 'none'; document.getElementById('2410.15060v1-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">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">5 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15019">arXiv:2410.15019</a> <span> [<a href="https://arxiv.org/pdf/2410.15019">pdf</a>, <a href="https://arxiv.org/format/2410.15019">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 Survey of Ontology Expansion for Conversational Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+J">Jinggui Liang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuxia Wu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a>, <a href="/search/cs?searchtype=author&query=Fei%2C+H">Hao Fei</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+L">Lizi Liao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15019v1-abstract-short" style="display: inline;"> In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational und… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15019v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15019v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15019v1-abstract-full" style="display: none;"> In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges. This survey aspires to be a foundational reference for researchers and practitioners, promoting further exploration and innovation in this crucial domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15019v1-abstract-full').style.display = 'none'; document.getElementById('2410.15019v1-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">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by EMNLP 2024, code and data are available at this https URL: https://github.com/liangjinggui/Ontology-Expansion</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14567">arXiv:2410.14567</a> <span> [<a href="https://arxiv.org/pdf/2410.14567">pdf</a>, <a href="https://arxiv.org/format/2410.14567">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> RAG-ConfusionQA: A Benchmark for Evaluating LLMs on Confusing Questions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Peng%2C+Z">Zhiyuan Peng</a>, <a href="/search/cs?searchtype=author&query=Nian%2C+J">Jinming Nian</a>, <a href="/search/cs?searchtype=author&query=Evfimievski%2C+A">Alexandre Evfimievski</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.14567v1-abstract-short" style="display: inline;"> Conversational AI agents use Retrieval Augmented Generation (RAG) to provide verifiable document-grounded responses to user inquiries. However, many natural questions do not have good answers: about 25\% contain false assumptions~\cite{Yu2023:CREPE}, and over 50\% are ambiguous~\cite{Min2020:AmbigQA}. RAG agents need high-quality data to improve their responses to confusing questions. This paper p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14567v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14567v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14567v1-abstract-full" style="display: none;"> Conversational AI agents use Retrieval Augmented Generation (RAG) to provide verifiable document-grounded responses to user inquiries. However, many natural questions do not have good answers: about 25\% contain false assumptions~\cite{Yu2023:CREPE}, and over 50\% are ambiguous~\cite{Min2020:AmbigQA}. RAG agents need high-quality data to improve their responses to confusing questions. This paper presents a novel synthetic data generation method to efficiently create a diverse set of context-grounded confusing questions from a given document corpus. We conduct an empirical comparative evaluation of several large language models as RAG agents to measure the accuracy of confusion detection and appropriate response generation. We contribute a benchmark dataset to the public domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14567v1-abstract-full').style.display = 'none'; document.getElementById('2410.14567v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/2410.12579">arXiv:2410.12579</a> <span> [<a href="https://arxiv.org/pdf/2410.12579">pdf</a>, <a href="https://arxiv.org/format/2410.12579">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Sensing-assisted Near-field Energy Beam Focusing with ELAA Over Non-stationary Channels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+Z">Zixiang Ren</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+L">Ling Qiu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jie Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.12579v1-abstract-short" style="display: inline;"> This paper studies a novel training-free energy beam focusing approach for a near-field wireless power transfer (WPT) system with extremely large-scale antenna array (ELAA). In particular, we focus on the setup with one access point (AP) equipped with an extremely large-scale uniform planar array (UPA) serving multiple single-antenna energy receivers (ERs), in which the line-of-sight (LoS) dominat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12579v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12579v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12579v1-abstract-full" style="display: none;"> This paper studies a novel training-free energy beam focusing approach for a near-field wireless power transfer (WPT) system with extremely large-scale antenna array (ELAA). In particular, we focus on the setup with one access point (AP) equipped with an extremely large-scale uniform planar array (UPA) serving multiple single-antenna energy receivers (ERs), in which the line-of-sight (LoS) dominated wireless channels are dependent on the relative positions of ERs and exhibit spatial non-stationarity. Different from conventional designs relying on training and feedback, we present a novel energy beam focusing design assisted by wireless radar sensing based on a two-stage transmission protocol. In the first stage, the AP performs wireless radar sensing to identify the ERs' visibility regions (VRs) and estimate their three-dimension (3D) positions for constructing the corresponding channel state information (CSI). In the second stage, the AP implements the transmit energy beam focusing based on the constructed CSI to efficiently charge these ERs. Under this setup, we first minimize the sensing duration in the first stage, while guaranteeing a specific accuracy threshold for position estimation. Next, we optimize the energy beamformers at the AP in the second stage to maximize the weighted harvested energy among all ERs subject to the maximum transmit power constraint. In this approach, the time resource allocation between the two stages is properly designed to optimize the ultimate energy transfer performance. Numerical results show that the proposed design performs close to the performance upper bound with perfect VR and CSI and significantly outperforms other benchmark schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12579v1-abstract-full').style.display = 'none'; document.getElementById('2410.12579v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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, 5 figures, received by Globecom Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11584">arXiv:2410.11584</a> <span> [<a href="https://arxiv.org/pdf/2410.11584">pdf</a>, <a href="https://arxiv.org/format/2410.11584">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wendi Chen</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+H">Han Xue</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+F">Fangyuan Zhou</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+C">Cewu 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="2410.11584v1-abstract-short" style="display: inline;"> In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when dealing with complex long-horizon deformable object tasks, such as high-dimensional state spaces, complex dynamics, and multimodal action distributions. Traditional imitation learning methods often require a large amount of data and encounter distributional shifts and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11584v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11584v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11584v1-abstract-full" style="display: none;"> In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when dealing with complex long-horizon deformable object tasks, such as high-dimensional state spaces, complex dynamics, and multimodal action distributions. Traditional imitation learning methods often require a large amount of data and encounter distributional shifts and accumulative errors in these tasks. To address these issues, we propose a data-efficient general learning framework (DeformPAM) based on preference learning and reward-guided action selection. DeformPAM decomposes long-horizon tasks into multiple action primitives, utilizes 3D point cloud inputs and diffusion models to model action distributions, and trains an implicit reward model using human preference data. During the inference phase, the reward model scores multiple candidate actions, selecting the optimal action for execution, thereby reducing the occurrence of anomalous actions and improving task completion quality. Experiments conducted on three challenging real-world long-horizon deformable object manipulation tasks demonstrate the effectiveness of this method. Results show that DeformPAM improves both task completion quality and efficiency compared to baseline methods even with limited data. Code and data will be available at https://deform-pam.robotflow.ai. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11584v1-abstract-full').style.display = 'none'; document.getElementById('2410.11584v1-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/2410.10901">arXiv:2410.10901</a> <span> [<a href="https://arxiv.org/pdf/2410.10901">pdf</a>, <a href="https://arxiv.org/format/2410.10901">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> 3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ding%2C+H">Hongxin Ding</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yue Fang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+R">Runchuan Zhu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xinke Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jinyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yongxin Xu</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+X">Xu Chu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Junfeng Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yasha 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="2410.10901v1-abstract-short" style="display: inline;"> Large Language Models(LLMs) excel in general tasks but struggle in specialized domains like healthcare due to limited domain-specific knowledge.Supervised Fine-Tuning(SFT) data construction for domain adaptation often relies on heuristic methods, such as GPT-4 annotation or manual data selection, with a data-centric focus on presumed diverse, high-quality datasets. However, these methods overlook… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10901v1-abstract-full').style.display = 'inline'; document.getElementById('2410.10901v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10901v1-abstract-full" style="display: none;"> Large Language Models(LLMs) excel in general tasks but struggle in specialized domains like healthcare due to limited domain-specific knowledge.Supervised Fine-Tuning(SFT) data construction for domain adaptation often relies on heuristic methods, such as GPT-4 annotation or manual data selection, with a data-centric focus on presumed diverse, high-quality datasets. However, these methods overlook the model's inherent knowledge distribution, introducing noise, redundancy, and irrelevant data, leading to a mismatch between the selected data and the model's learning task, resulting in suboptimal performance. To address this, we propose a two-stage model-centric data selection framework, Decomposed Difficulty Data Selection (3DS), which aligns data with the model's knowledge distribution for optimized adaptation. In Stage1, we apply Prompt-Driven Data Selection via Explicit Alignment, where the the model filters irrelevant or redundant data based on its internal knowledge. In Stage2, we perform Decomposed Difficulty Data Selection, where data selection is guided by our defined difficulty decomposition, using three metrics: Instruction Understanding, Response Confidence, and Response Correctness. Additionally, an attention-based importance weighting mechanism captures token importance for more accurate difficulty calibration. This two-stage approach ensures the selected data is not only aligned with the model's knowledge and preferences but also appropriately challenging for the model to learn, leading to more effective and targeted domain adaptation. In the case study of the medical domain, our extensive experiments on real-world healthcare datasets demonstrate the superiority of 3DS over exisiting methods in accuracy by over 5.29%. Our dataset and code will be open-sourced at https://anonymous.4open.science/r/3DS-E67F. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10901v1-abstract-full').style.display = 'none'; document.getElementById('2410.10901v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09123">arXiv:2410.09123</a> <span> [<a href="https://arxiv.org/pdf/2410.09123">pdf</a>, <a href="https://arxiv.org/format/2410.09123">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"> Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+R">Ran Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhongzhou Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoli Li</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.09123v2-abstract-short" style="display: inline;"> Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approaches have emerged, utilizing techniques such as meta-learning. However, the assumption is that novel relations in meta-testing and base relations in m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09123v2-abstract-full').style.display = 'inline'; document.getElementById('2410.09123v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09123v2-abstract-full" style="display: none;"> Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approaches have emerged, utilizing techniques such as meta-learning. However, the assumption is that novel relations in meta-testing and base relations in meta-training are independently and identically distributed, which may not hold in practice. To address the limitation, we propose RelAdapter, a context-aware adapter for few-shot relation learning in KGs designed to enhance the adaptation process in meta-learning. First, RelAdapter is equipped with a lightweight adapter module that facilitates relation-specific, tunable adaptation of meta-knowledge in a parameter-efficient manner. Second, RelAdapter is enriched with contextual information about the target relation, enabling enhanced adaptation to each distinct relation. Extensive experiments on three benchmark KGs validate the superiority of RelAdapter over state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09123v2-abstract-full').style.display = 'none'; document.getElementById('2410.09123v2-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 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by EMNLP 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/2410.08696">arXiv:2410.08696</a> <span> [<a href="https://arxiv.org/pdf/2410.08696">pdf</a>, <a href="https://arxiv.org/format/2410.08696">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"> AMPO: Automatic Multi-Branched Prompt Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sheng Yang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yurong Wu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yan Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zineng Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+B+B">Bin Benjamin Zhu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xiaodi Sun</a>, <a href="/search/cs?searchtype=author&query=Lou%2C+J">Jian-Guang Lou</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Zhiming Ding</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+A">Anbang Hu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunsong Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junyan Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Linjun Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.08696v1-abstract-short" style="display: inline;"> Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize the prompts, achieving satisfying results. However, existing automatic prompt optimization techniques are only limited to producing single flow instructions, stru… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08696v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08696v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08696v1-abstract-full" style="display: none;"> Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize the prompts, achieving satisfying results. However, existing automatic prompt optimization techniques are only limited to producing single flow instructions, struggling with handling diverse patterns. In this paper, we present AMPO, an automatic prompt optimization method that can iteratively develop a multi-branched prompt using failure cases as feedback. Our goal is to explore a novel way of structuring prompts with multi-branches to better handle multiple patterns in complex tasks, for which we introduce three modules: Pattern Recognition, Branch Adjustment, and Branch Pruning. In experiments across five tasks, AMPO consistently achieves the best results. Additionally, our approach demonstrates significant optimization efficiency due to our adoption of a minimal search strategy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08696v1-abstract-full').style.display = 'none'; document.getElementById('2410.08696v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 7 figures, 6 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/2410.07592">arXiv:2410.07592</a> <span> [<a href="https://arxiv.org/pdf/2410.07592">pdf</a>, <a href="https://arxiv.org/format/2410.07592">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Diversified and Adaptive Negative Sampling on Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+R">Ran Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhongzhou Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoli Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hao Wu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.07592v1-abstract-short" style="display: inline;"> In knowledge graph embedding, aside from positive triplets (ie: facts in the knowledge graph), the negative triplets used for training also have a direct influence on the model performance. In reality, since knowledge graphs are sparse and incomplete, negative triplets often lack explicit labels, and thus they are often obtained from various sampling strategies (eg: randomly replacing an entity in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07592v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07592v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07592v1-abstract-full" style="display: none;"> In knowledge graph embedding, aside from positive triplets (ie: facts in the knowledge graph), the negative triplets used for training also have a direct influence on the model performance. In reality, since knowledge graphs are sparse and incomplete, negative triplets often lack explicit labels, and thus they are often obtained from various sampling strategies (eg: randomly replacing an entity in a positive triplet). An ideal sampled negative triplet should be informative enough to help the model train better. However, existing methods often ignore diversity and adaptiveness in their sampling process, which harms the informativeness of negative triplets. As such, we propose a generative adversarial approach called Diversified and Adaptive Negative Sampling DANS on knowledge graphs. DANS is equipped with a two-way generator that generates more diverse negative triplets through two pathways, and an adaptive mechanism that produces more fine-grained examples by localizing the global generator for different entities and relations. On the one hand, the two-way generator increase the overall informativeness with more diverse negative examples; on the other hand, the adaptive mechanism increases the individual sample-wise informativeness with more fine-grained sampling. Finally, we evaluate the performance of DANS on three benchmark knowledge graphs to demonstrate its effectiveness through quantitative and qualitative experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07592v1-abstract-full').style.display = 'none'; document.getElementById('2410.07592v1-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">30 pages, 7 figures, Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07078">arXiv:2410.07078</a> <span> [<a href="https://arxiv.org/pdf/2410.07078">pdf</a>, <a href="https://arxiv.org/format/2410.07078">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yishu Li</a>, <a href="/search/cs?searchtype=author&query=Leng%2C+W+H">Wen Hui Leng</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yiming Fang</a>, <a href="/search/cs?searchtype=author&query=Eisner%2C+B">Ben Eisner</a>, <a href="/search/cs?searchtype=author&query=Held%2C+D">David Held</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="2410.07078v2-abstract-short" style="display: inline;"> We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation modes: for instance, when the articulation direction (e.g. push, pull, slide) or location (e.g. left side, right side) of a fully closed door are uncertain, or when… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07078v2-abstract-full').style.display = 'inline'; document.getElementById('2410.07078v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07078v2-abstract-full" style="display: none;"> We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation modes: for instance, when the articulation direction (e.g. push, pull, slide) or location (e.g. left side, right side) of a fully closed door are uncertain, or when distinguishing features like the plane of the door are occluded due to the viewing angle. To tackle these challenges, we propose a history-aware diffusion network that can model multi-modal distributions over articulation modes for articulated objects; our method further uses observation history to distinguish between modes and make stable predictions under occlusions. Experiments and analysis demonstrate that our method achieves state-of-art performance on articulated object manipulation and dramatically improves performance for articulated objects containing visual ambiguities. Our project website is available at https://flowbothd.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07078v2-abstract-full').style.display = 'none'; document.getElementById('2410.07078v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 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">Accepted to CoRL 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/2410.05797">arXiv:2410.05797</a> <span> [<a href="https://arxiv.org/pdf/2410.05797">pdf</a>, <a href="https://arxiv.org/format/2410.05797">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"> CodeCipher: Learning to Obfuscate Source Code Against LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yalan Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+C">Chengcheng Wan</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yixiong Fang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+X">Xiaodong Gu</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="2410.05797v1-abstract-short" style="display: inline;"> While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized training, reading, and execution of the user code. In this paper, we propose CodeCipher, a novel method that perturbs privacy from code while preserving the ori… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05797v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05797v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05797v1-abstract-full" style="display: none;"> While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized training, reading, and execution of the user code. In this paper, we propose CodeCipher, a novel method that perturbs privacy from code while preserving the original response from LLMs. CodeCipher transforms the LLM's embedding matrix so that each row corresponds to a different word in the original matrix, forming a token-to-token confusion mapping for obfuscating source code. The new embedding matrix is optimized by minimizing the task-specific loss function. To tackle the challenge of the discrete and sparse nature of word vector spaces, CodeCipher adopts a discrete optimization strategy that aligns the updated vector to the nearest valid token in the vocabulary before each gradient update. We demonstrate the effectiveness of our approach on three AI-assisted coding tasks including code completion, summarization, and translation. Results show that our model successfully confuses the privacy in source code while preserving the original LLM's performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05797v1-abstract-full').style.display = 'none'; document.getElementById('2410.05797v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04320">arXiv:2410.04320</a> <span> [<a href="https://arxiv.org/pdf/2410.04320">pdf</a>, <a href="https://arxiv.org/format/2410.04320">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=An%2C+H">Haonan An</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zhengru Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuang Zhang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Senkang Hu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xianhao Chen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+G">Guowen Xu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuguang Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.04320v1-abstract-short" style="display: inline;"> Connected and autonomous vehicles (CAVs) have garnered significant attention due to their extended perception range and enhanced sensing coverage. To address challenges such as blind spots and obstructions, CAVs employ vehicle-to-vehicle (V2V) communications to aggregate sensory data from surrounding vehicles. However, cooperative perception is often constrained by the limitations of achievable ne… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04320v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04320v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04320v1-abstract-full" style="display: none;"> Connected and autonomous vehicles (CAVs) have garnered significant attention due to their extended perception range and enhanced sensing coverage. To address challenges such as blind spots and obstructions, CAVs employ vehicle-to-vehicle (V2V) communications to aggregate sensory data from surrounding vehicles. However, cooperative perception is often constrained by the limitations of achievable network throughput and channel quality. In this paper, we propose a channel-aware throughput maximization approach to facilitate CAV data fusion, leveraging a self-supervised autoencoder for adaptive data compression. We formulate the problem as a mixed integer programming (MIP) model, which we decompose into two sub-problems to derive optimal data rate and compression ratio solutions under given link conditions. An autoencoder is then trained to minimize bitrate with the determined compression ratio, and a fine-tuning strategy is employed to further reduce spectrum resource consumption. Experimental evaluation on the OpenCOOD platform demonstrates the effectiveness of our proposed algorithm, showing more than 20.19\% improvement in network throughput and a 9.38\% increase in average precision (AP@IoU) compared to state-of-the-art methods, with an optimal latency of 19.99 ms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04320v1-abstract-full').style.display = 'none'; document.getElementById('2410.04320v1-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 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/2410.04168">arXiv:2410.04168</a> <span> [<a href="https://arxiv.org/pdf/2410.04168">pdf</a>, <a href="https://arxiv.org/format/2410.04168">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> R-ACP: Real-Time Adaptive Collaborative Perception Leveraging Robust Task-Oriented Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zhengru Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingjing Wang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yanan Ma</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Y">Yihang Tao</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Yiqin Deng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xianhao Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuguang Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.04168v3-abstract-short" style="display: inline;"> Collaborative perception enhances sensing in multi-robot and vehicular networks by fusing information from multiple agents, improving perception accuracy and sensing range. However, mobility and non-rigid sensor mounts introduce extrinsic calibration errors, necessitating online calibration, further complicated by limited overlap in sensing regions. Moreover, maintaining fresh information is cruci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04168v3-abstract-full').style.display = 'inline'; document.getElementById('2410.04168v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04168v3-abstract-full" style="display: none;"> Collaborative perception enhances sensing in multi-robot and vehicular networks by fusing information from multiple agents, improving perception accuracy and sensing range. However, mobility and non-rigid sensor mounts introduce extrinsic calibration errors, necessitating online calibration, further complicated by limited overlap in sensing regions. Moreover, maintaining fresh information is crucial for timely and accurate sensing. To address calibration errors and ensure timely and accurate perception, we propose a robust task-oriented communication strategy to optimize online self-calibration and efficient feature sharing for Real-time Adaptive Collaborative Perception (R-ACP). Specifically, we first formulate an Age of Perceived Targets (AoPT) minimization problem to capture data timeliness of multi-view streaming. Then, in the calibration phase, we introduce a channel-aware self-calibration technique based on re-identification (Re-ID), which adaptively compresses key features according to channel capacities, effectively addressing calibration issues via spatial and temporal cross-camera correlations. In the streaming phase, we tackle the trade-off between bandwidth and inference accuracy by leveraging an Information Bottleneck (IB) based encoding method to adjust video compression rates based on task relevance, thereby reducing communication overhead and latency. Finally, we design a priority-aware network to filter corrupted features to mitigate performance degradation from packet corruption. Extensive studies demonstrate that our framework outperforms five baselines, improving multiple object detection accuracy (MODA) by 25.49% and reducing communication costs by 51.36% under severely poor channel conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04168v3-abstract-full').style.display = 'none'; document.getElementById('2410.04168v3-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">v1</span> submitted 5 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/2410.02720">arXiv:2410.02720</a> <span> [<a href="https://arxiv.org/pdf/2410.02720">pdf</a>, <a href="https://arxiv.org/format/2410.02720">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"> Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+M">Mengxi Wu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao Huang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a>, <a href="/search/cs?searchtype=author&query=Rostami%2C+M">Mohammad Rostami</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="2410.02720v2-abstract-short" style="display: inline;"> Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To tackle this challenge, we propose \textbf{C}urvature \textbf{D}iversity-Driven \textbf{N}uclear-Norm Wasserstein \textbf{D}omain Alignment (CDND). Our approach first… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02720v2-abstract-full').style.display = 'inline'; document.getElementById('2410.02720v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02720v2-abstract-full" style="display: none;"> Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To tackle this challenge, we propose \textbf{C}urvature \textbf{D}iversity-Driven \textbf{N}uclear-Norm Wasserstein \textbf{D}omain Alignment (CDND). Our approach first introduces a \textit{\textbf{Curv}ature Diversity-driven Deformation \textbf{Rec}onstruction (CurvRec)} task, which effectively mitigates the gap between the source and target domains by enabling the model to extract salient features from semantically rich regions of a given point cloud. We then propose \textit{\textbf{D}eformation-based \textbf{N}uclear-norm \textbf{W}asserstein \textbf{D}iscrepancy (D-NWD)}, which applies the Nuclear-norm Wasserstein Discrepancy to both \textit{deformed and original} data samples to align the source and target domains. Furthermore, we contribute a theoretical justification for the effectiveness of D-NWD in distribution alignment and demonstrate that it is \textit{generic} enough to be applied to \textbf{any} deformations. To validate our method, we conduct extensive experiments on two public domain adaptation datasets for point cloud classification and segmentation tasks. Empirical experiment results show that our CDND achieves state-of-the-art performance by a noticeable margin over existing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02720v2-abstract-full').style.display = 'none'; document.getElementById('2410.02720v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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/2410.02592">arXiv:2410.02592</a> <span> [<a href="https://arxiv.org/pdf/2410.02592">pdf</a>, <a href="https://arxiv.org/format/2410.02592">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zihan Fang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zheng Lin</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Senkang Hu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+H">Hangcheng Cao</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Yiqin Deng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xianhao Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuguang Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.02592v4-abstract-short" style="display: inline;"> Recently, in-car monitoring has emerged as a promising technology for detecting early-stage abnormal status of the driver and providing timely alerts to prevent traffic accidents. Although training models with multimodal data enhances the reliability of abnormal status detection, the scarcity of labeled data and the imbalance of class distribution impede the extraction of critical abnormal state f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02592v4-abstract-full').style.display = 'inline'; document.getElementById('2410.02592v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02592v4-abstract-full" style="display: none;"> Recently, in-car monitoring has emerged as a promising technology for detecting early-stage abnormal status of the driver and providing timely alerts to prevent traffic accidents. Although training models with multimodal data enhances the reliability of abnormal status detection, the scarcity of labeled data and the imbalance of class distribution impede the extraction of critical abnormal state features, significantly deteriorating training performance. Furthermore, missing modalities due to environment and hardware limitations further exacerbate the challenge of abnormal status identification. More importantly, monitoring abnormal health conditions of passengers, particularly in elderly care, is of paramount importance but remains underexplored. To address these challenges, we introduce our IC3M, an efficient camera-rotation-based multimodal framework for monitoring both driver and passengers in a car. Our IC3M comprises two key modules: an adaptive threshold pseudo-labeling strategy and a missing modality reconstruction. The former customizes pseudo-labeling thresholds for different classes based on the class distribution, generating class-balanced pseudo labels to guide model training effectively, while the latter leverages crossmodality relationships learned from limited labels to accurately recover missing modalities by distribution transferring from available modalities. Extensive experimental results demonstrate that IC3M outperforms state-of-the-art benchmarks in accuracy, precision, and recall while exhibiting superior robustness under limited labeled data and severe missing modality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02592v4-abstract-full').style.display = 'none'; document.getElementById('2410.02592v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 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/2410.01840">arXiv:2410.01840</a> <span> [<a href="https://arxiv.org/pdf/2410.01840">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> Target Pose Guided Whole-body Grasping Motion Generation for Digital Humans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shao%2C+Q">Quanquan Shao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.01840v1-abstract-short" style="display: inline;"> Grasping manipulation is a fundamental mode for human interaction with daily life objects. The synthesis of grasping motion is also greatly demanded in many applications such as animation and robotics. In objects grasping research field, most works focus on generating the last static grasping pose with a parallel gripper or dexterous hand. Grasping motion generation for the full arm especially for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01840v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01840v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01840v1-abstract-full" style="display: none;"> Grasping manipulation is a fundamental mode for human interaction with daily life objects. The synthesis of grasping motion is also greatly demanded in many applications such as animation and robotics. In objects grasping research field, most works focus on generating the last static grasping pose with a parallel gripper or dexterous hand. Grasping motion generation for the full arm especially for the full humanlike intelligent agent is still under-explored. In this work, we propose a grasping motion generation framework for digital human which is an anthropomorphic intelligent agent with high degrees of freedom in virtual world. Given an object known initial pose in 3D space, we first generate a target pose for whole-body digital human based on off-the-shelf target grasping pose generation methods. With an initial pose and this generated target pose, a transformer-based neural network is used to generate the whole grasping trajectory, which connects initial pose and target pose smoothly and naturally. Additionally, two post optimization components are designed to mitigates foot-skating issue and hand-object interpenetration separately. Experiments are conducted on GRAB dataset to demonstrate effectiveness of this proposed method for whole-body grasping motion generation with randomly placed unknown objects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01840v1-abstract-full').style.display = 'none'; document.getElementById('2410.01840v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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">7 pages,5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00070">arXiv:2410.00070</a> <span> [<a href="https://arxiv.org/pdf/2410.00070">pdf</a>, <a href="https://arxiv.org/format/2410.00070">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</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="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Mamba for Streaming ASR Combined with Unimodal Aggregation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Ying Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaofei 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="2410.00070v1-abstract-short" style="display: inline;"> This paper works on streaming automatic speech recognition (ASR). Mamba, a recently proposed state space model, has demonstrated the ability to match or surpass Transformers in various tasks while benefiting from a linear complexity advantage. We explore the efficiency of Mamba encoder for streaming ASR and propose an associated lookahead mechanism for leveraging controllable future information. A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00070v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00070v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00070v1-abstract-full" style="display: none;"> This paper works on streaming automatic speech recognition (ASR). Mamba, a recently proposed state space model, has demonstrated the ability to match or surpass Transformers in various tasks while benefiting from a linear complexity advantage. We explore the efficiency of Mamba encoder for streaming ASR and propose an associated lookahead mechanism for leveraging controllable future information. Additionally, a streaming-style unimodal aggregation (UMA) method is implemented, which automatically detects token activity and streamingly triggers token output, and meanwhile aggregates feature frames for better learning token representation. Based on UMA, an early termination (ET) method is proposed to further reduce recognition latency. Experiments conducted on two Mandarin Chinese datasets demonstrate that the proposed model achieves competitive ASR performance in terms of both recognition accuracy and latency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00070v1-abstract-full').style.display = 'none'; document.getElementById('2410.00070v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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">Submitted to ICASSP 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.20111">arXiv:2409.20111</a> <span> [<a href="https://arxiv.org/pdf/2409.20111">pdf</a>, <a href="https://arxiv.org/format/2409.20111">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Robust Gaussian Splatting SLAM by Leveraging Loop Closure </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zunjie Zhu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Youxu Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xin Li</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+C">Chengang Yan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+F">Feng Xu</a>, <a href="/search/cs?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanyan 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="2409.20111v1-abstract-short" style="display: inline;"> 3D Gaussian Splatting algorithms excel in novel view rendering applications and have been adapted to extend the capabilities of traditional SLAM systems. However, current Gaussian Splatting SLAM methods, designed mainly for hand-held RGB or RGB-D sensors, struggle with tracking drifts when used with rotating RGB-D camera setups. In this paper, we propose a robust Gaussian Splatting SLAM architectu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20111v1-abstract-full').style.display = 'inline'; document.getElementById('2409.20111v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.20111v1-abstract-full" style="display: none;"> 3D Gaussian Splatting algorithms excel in novel view rendering applications and have been adapted to extend the capabilities of traditional SLAM systems. However, current Gaussian Splatting SLAM methods, designed mainly for hand-held RGB or RGB-D sensors, struggle with tracking drifts when used with rotating RGB-D camera setups. In this paper, we propose a robust Gaussian Splatting SLAM architecture that utilizes inputs from rotating multiple RGB-D cameras to achieve accurate localization and photorealistic rendering performance. The carefully designed Gaussian Splatting Loop Closure module effectively addresses the issue of accumulated tracking and mapping errors found in conventional Gaussian Splatting SLAM systems. First, each Gaussian is associated with an anchor frame and categorized as historical or novel based on its timestamp. By rendering different types of Gaussians at the same viewpoint, the proposed loop detection strategy considers both co-visibility relationships and distinct rendering outcomes. Furthermore, a loop closure optimization approach is proposed to remove camera pose drift and maintain the high quality of 3D Gaussian models. The approach uses a lightweight pose graph optimization algorithm to correct pose drift and updates Gaussians based on the optimized poses. Additionally, a bundle adjustment scheme further refines camera poses using photometric and geometric constraints, ultimately enhancing the global consistency of scenarios. Quantitative and qualitative evaluations on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art methods in camera pose estimation and novel view rendering tasks. The code will be open-sourced for the community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20111v1-abstract-full').style.display = 'none'; document.getElementById('2409.20111v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19821">arXiv:2409.19821</a> <span> [<a href="https://arxiv.org/pdf/2409.19821">pdf</a>, <a href="https://arxiv.org/format/2409.19821">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"> Tracking Everything in Robotic-Assisted Surgery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhan%2C+B">Bohan Zhan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wang Zhao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a>, <a href="/search/cs?searchtype=author&query=Du%2C+B">Bo Du</a>, <a href="/search/cs?searchtype=author&query=Vasconcelos%2C+F">Francisco Vasconcelos</a>, <a href="/search/cs?searchtype=author&query=Stoyanov%2C+D">Danail Stoyanov</a>, <a href="/search/cs?searchtype=author&query=Elson%2C+D+S">Daniel S. Elson</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+B">Baoru Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.19821v1-abstract-short" style="display: inline;"> Accurate tracking of tissues and instruments in videos is crucial for Robotic-Assisted Minimally Invasive Surgery (RAMIS), as it enables the robot to comprehend the surgical scene with precise locations and interactions of tissues and tools. Traditional keypoint-based sparse tracking is limited by featured points, while flow-based dense two-view matching suffers from long-term drifts. Recently, th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19821v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19821v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19821v1-abstract-full" style="display: none;"> Accurate tracking of tissues and instruments in videos is crucial for Robotic-Assisted Minimally Invasive Surgery (RAMIS), as it enables the robot to comprehend the surgical scene with precise locations and interactions of tissues and tools. Traditional keypoint-based sparse tracking is limited by featured points, while flow-based dense two-view matching suffers from long-term drifts. Recently, the Tracking Any Point (TAP) algorithm was proposed to overcome these limitations and achieve dense accurate long-term tracking. However, its efficacy in surgical scenarios remains untested, largely due to the lack of a comprehensive surgical tracking dataset for evaluation. To address this gap, we introduce a new annotated surgical tracking dataset for benchmarking tracking methods for surgical scenarios, comprising real-world surgical videos with complex tissue and instrument motions. We extensively evaluate state-of-the-art (SOTA) TAP-based algorithms on this dataset and reveal their limitations in challenging surgical scenarios, including fast instrument motion, severe occlusions, and motion blur, etc. Furthermore, we propose a new tracking method, namely SurgMotion, to solve the challenges and further improve the tracking performance. Our proposed method outperforms most TAP-based algorithms in surgical instruments tracking, and especially demonstrates significant improvements over baselines in challenging medical videos. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19821v1-abstract-full').style.display = 'none'; document.getElementById('2409.19821v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19804">arXiv:2409.19804</a> <span> [<a href="https://arxiv.org/pdf/2409.19804">pdf</a>, <a href="https://arxiv.org/format/2409.19804">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"> Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xuyang Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuowei Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hsin-Tai Wu</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhiqiang Tao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.19804v1-abstract-short" style="display: inline;"> RAG (Retrieval-Augmented Generation) have recently gained significant attention for their enhanced ability to integrate external knowledge sources in open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as languag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19804v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19804v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19804v1-abstract-full" style="display: none;"> RAG (Retrieval-Augmented Generation) have recently gained significant attention for their enhanced ability to integrate external knowledge sources in open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness may have been largely overlooked. Second, RAG methods are complex pipelines, making it hard to identify and address biases, as each component is optimized for different goals. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG methods, using scenario-based questions and analyzing disparities across demographic attributes. The experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages, highlighting the need for more targeted fairness interventions within RAG pipelines. We will release our dataset and code upon acceptance of the paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19804v1-abstract-full').style.display = 'none'; document.getElementById('2409.19804v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/2409.19548">arXiv:2409.19548</a> <span> [<a href="https://arxiv.org/pdf/2409.19548">pdf</a>, <a href="https://arxiv.org/format/2409.19548">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3698876">10.1145/3698876 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Meta Learning to Rank for Sparsely Supervised Queries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xuyang Wu</a>, <a href="/search/cs?searchtype=author&query=Puthenputhussery%2C+A">Ajit Puthenputhussery</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+H">Hongwei Shang</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+C">Changsung Kang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.19548v1-abstract-short" style="display: inline;"> Supervisory signals are a critical resource for training learning to rank models. In many real-world search and retrieval scenarios, these signals may not be readily available or could be costly to obtain for some queries. The examples include domains where labeling requires professional expertise, applications with strong privacy constraints, and user engagement information that are too scarce. W… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19548v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19548v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19548v1-abstract-full" style="display: none;"> Supervisory signals are a critical resource for training learning to rank models. In many real-world search and retrieval scenarios, these signals may not be readily available or could be costly to obtain for some queries. The examples include domains where labeling requires professional expertise, applications with strong privacy constraints, and user engagement information that are too scarce. We refer to these scenarios as sparsely supervised queries which pose significant challenges to traditional learning to rank models. In this work, we address sparsely supervised queries by proposing a novel meta learning to rank framework which leverages fast learning and adaption capability of meta-learning. The proposed approach accounts for the fact that different queries have different optimal parameters for their rankers, in contrast to traditional learning to rank models which only learn a global ranking model applied to all the queries. In consequence, the proposed method would yield significant advantages especially when new queries are of different characteristics with the training queries. Moreover, the proposed meta learning to rank framework is generic and flexible. We conduct a set of comprehensive experiments on both public datasets and a real-world e-commerce dataset. The results demonstrate that the proposed meta-learning approach can significantly enhance the performance of learning to rank models with sparsely labeled queries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19548v1-abstract-full').style.display = 'none'; document.getElementById('2409.19548v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at TOIS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16605">arXiv:2409.16605</a> <span> [<a href="https://arxiv.org/pdf/2409.16605">pdf</a>, <a href="https://arxiv.org/format/2409.16605">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <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"> Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+E">Ethan Lin</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Z">Zhiyuan Peng</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.16605v1-abstract-short" style="display: inline;"> Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly pap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16605v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16605v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16605v1-abstract-full" style="display: none;"> Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly papers. SchNovel consists of 15000 pairs of papers across six fields sampled from the arXiv dataset with publication dates spanning 2 to 10 years apart. In each pair, the more recently published paper is assumed to be more novel. Additionally, we propose RAG-Novelty, which simulates the review process taken by human reviewers by leveraging the retrieval of similar papers to assess novelty. Extensive experiments provide insights into the capabilities of different LLMs to assess novelty and demonstrate that RAG-Novelty outperforms recent baseline models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16605v1-abstract-full').style.display = 'none'; document.getElementById('2409.16605v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/2409.16455">arXiv:2409.16455</a> <span> [<a href="https://arxiv.org/pdf/2409.16455">pdf</a>, <a href="https://arxiv.org/format/2409.16455">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> MultiTalk: Introspective and Extrospective Dialogue for Human-Environment-LLM Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Devarakonda%2C+V+N">Venkata Naren Devarakonda</a>, <a href="/search/cs?searchtype=author&query=Kaypak%2C+A+U">Ali Umut Kaypak</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuaihang Yuan</a>, <a href="/search/cs?searchtype=author&query=Krishnamurthy%2C+P">Prashanth Krishnamurthy</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yi Fang</a>, <a href="/search/cs?searchtype=author&query=Khorrami%2C+F">Farshad Khorrami</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.16455v1-abstract-short" style="display: inline;"> LLMs have shown promising results in task planning due to their strong natural language understanding and reasoning capabilities. However, issues such as hallucinations, ambiguities in human instructions, environmental constraints, and limitations in the executing agent's capabilities often lead to flawed or incomplete plans. This paper proposes MultiTalk, an LLM-based task planning methodology th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16455v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16455v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16455v1-abstract-full" style="display: none;"> LLMs have shown promising results in task planning due to their strong natural language understanding and reasoning capabilities. However, issues such as hallucinations, ambiguities in human instructions, environmental constraints, and limitations in the executing agent's capabilities often lead to flawed or incomplete plans. This paper proposes MultiTalk, an LLM-based task planning methodology that addresses these issues through a framework of introspective and extrospective dialogue loops. This approach helps ground generated plans in the context of the environment and the agent's capabilities, while also resolving uncertainties and ambiguities in the given task. These loops are enabled by specialized systems designed to extract and predict task-specific states, and flag mismatches or misalignments among the human user, the LLM agent, and the environment. Effective feedback pathways between these systems and the LLM planner foster meaningful dialogue. The efficacy of this methodology is demonstrated through its application to robotic manipulation tasks. Experiments and ablations highlight the robustness and reliability of our method, and comparisons with baselines further illustrate the superiority of MultiTalk in task planning for embodied agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16455v1-abstract-full').style.display = 'none'; document.getElementById('2409.16455v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 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/2409.15734">arXiv:2409.15734</a> <span> [<a href="https://arxiv.org/pdf/2409.15734">pdf</a>, <a href="https://arxiv.org/format/2409.15734">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</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="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</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"> Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuchen Fang</a>, <a href="/search/cs?searchtype=author&query=Na%2C+S">Sen Na</a>, <a href="/search/cs?searchtype=author&query=Mahoney%2C+M+W">Michael W. Mahoney</a>, <a href="/search/cs?searchtype=author&query=Kolar%2C+M">Mladen Kolar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.15734v2-abstract-short" style="display: inline;"> In this work, we consider solving optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Sequential Quadratic Programming method to find both first- and second-order stationary points. Our method utilizes a random model to represent the objective function, which is constructed from stochastic observations of the objective and is designed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15734v2-abstract-full').style.display = 'inline'; document.getElementById('2409.15734v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15734v2-abstract-full" style="display: none;"> In this work, we consider solving optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Sequential Quadratic Programming method to find both first- and second-order stationary points. Our method utilizes a random model to represent the objective function, which is constructed from stochastic observations of the objective and is designed to satisfy proper adaptive accuracy conditions with a high but fixed probability. To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a quadratic approximation of the objective subject to a (relaxed) linear approximation of the problem constraints and a trust-region constraint. To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature of the reduced Hessian matrix, as well as a second-order correction step to address the potential Maratos effect, which arises due to the nonlinearity of the problem constraints. Such an effect may impede the method from moving away from saddle points. Both gradient and eigen step computations leverage a novel parameter-free decomposition of the step and the trust-region radius, accounting for the proportions among the feasibility residual, optimality residual, and negative curvature. We establish global almost sure first- and second-order convergence guarantees for our method, and present computational results on CUTEst problems, regression problems, and saddle-point problems to demonstrate its superiority over existing line-search-based stochastic methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15734v2-abstract-full').style.display = 'none'; document.getElementById('2409.15734v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">41 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/2409.15049">arXiv:2409.15049</a> <span> [<a href="https://arxiv.org/pdf/2409.15049">pdf</a>, <a href="https://arxiv.org/format/2409.15049">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"> PackageIntel: Leveraging Large Language Models for Automated Intelligence Extraction in Package Ecosystems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+W">Wenbo Guo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chengwei Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Limin Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiahui Wu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhengzi Xu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+C">Cheng Huang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yong Fang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang 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="2409.15049v2-abstract-short" style="display: inline;"> The rise of malicious packages in public registries poses a significant threat to software supply chain (SSC) security. Although academia and industry employ methods like software composition analysis (SCA) to address this issue, existing approaches often lack timely and comprehensive intelligence updates. This paper introduces PackageIntel, a novel platform that revolutionizes the collection, pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15049v2-abstract-full').style.display = 'inline'; document.getElementById('2409.15049v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15049v2-abstract-full" style="display: none;"> The rise of malicious packages in public registries poses a significant threat to software supply chain (SSC) security. Although academia and industry employ methods like software composition analysis (SCA) to address this issue, existing approaches often lack timely and comprehensive intelligence updates. This paper introduces PackageIntel, a novel platform that revolutionizes the collection, processing, and retrieval of malicious package intelligence. By utilizing exhaustive search techniques, snowball sampling from diverse sources, and large language models (LLMs) with specialized prompts, PackageIntel ensures enhanced coverage, timeliness, and accuracy. We have developed a comprehensive database containing 20,692 malicious NPM and PyPI packages sourced from 21 distinct intelligence repositories. Empirical evaluations demonstrate that PackageIntel achieves a precision of 98.6% and an F1 score of 92.0 in intelligence extraction. Additionally, it detects threats on average 70% earlier than leading databases like Snyk and OSV, and operates cost-effectively at $0.094 per intelligence piece. The platform has successfully identified and reported over 1,000 malicious packages in downstream package manager mirror registries. This research provides a robust, efficient, and timely solution for identifying and mitigating threats within the software supply chain ecosystem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15049v2-abstract-full').style.display = 'none'; document.getElementById('2409.15049v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14738">arXiv:2409.14738</a> <span> [<a href="https://arxiv.org/pdf/2409.14738">pdf</a>, <a href="https://arxiv.org/format/2409.14738">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Enabling On-Chip High-Frequency Adaptive Linear Optimal Control via Linearized Gaussian Process </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yuan Gao</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+Y">Yinyi Lai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yini Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14738v2-abstract-short" style="display: inline;"> Unpredictable and complex aerodynamic effects pose significant challenges to achieving precise flight control, such as the downwash effect from upper vehicles to lower ones. Conventional methods often struggle to accurately model these interactions, leading to controllers that require large safety margins between vehicles. Moreover, the controller on real drones usually requires high-frequency and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14738v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14738v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14738v2-abstract-full" style="display: none;"> Unpredictable and complex aerodynamic effects pose significant challenges to achieving precise flight control, such as the downwash effect from upper vehicles to lower ones. Conventional methods often struggle to accurately model these interactions, leading to controllers that require large safety margins between vehicles. Moreover, the controller on real drones usually requires high-frequency and has limited on-chip computation, making the adaptive control design more difficult to implement. To address these challenges, we incorporate Gaussian process (GP) to model the adaptive external aerodynamics with linear model predictive control. The GP is linearized to enable real-time high-frequency solutions. Moreover, to handle the error caused by linearization, we integrate end-to-end Bayesian optimization during sample collection stages to improve the control performance. Experimental results on both simulations and real quadrotors show that we can achieve real-time solvable computation speed with acceptable tracking errors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14738v2-abstract-full').style.display = 'none'; document.getElementById('2409.14738v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14106">arXiv:2409.14106</a> <span> [<a href="https://arxiv.org/pdf/2409.14106">pdf</a>, <a href="https://arxiv.org/format/2409.14106">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> FineMolTex: Towards Fine-grained Molecular Graph-Text Pre-training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yibo Li</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuan Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengmei Zhang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+C">Chuan Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14106v2-abstract-short" style="display: inline;"> Understanding molecular structure and related knowledge is crucial for scientific research. Recent studies integrate molecular graphs with their textual descriptions to enhance molecular representation learning. However, they focus on the whole molecular graph and neglect frequently occurring subgraphs, known as motifs,which are essential for determining molecular properties. Without such fine-gra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14106v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14106v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14106v2-abstract-full" style="display: none;"> Understanding molecular structure and related knowledge is crucial for scientific research. Recent studies integrate molecular graphs with their textual descriptions to enhance molecular representation learning. However, they focus on the whole molecular graph and neglect frequently occurring subgraphs, known as motifs,which are essential for determining molecular properties. Without such fine-grained knowledge, these models struggle to generalize to unseen molecules and tasks that require motif-level insights. To bridge this gap, we propose FineMolTex, a novel Fine-grained Molecular graph-Text pre-training framework to jointly learn coarse-grained molecule-level knowledge and fine-grained motif-level knowledge. Specifically, FineMolTex consists of two pre-training tasks: a contrastive alignment task for coarse-grained matching and a masked multi-modal modeling task for fine-grained matching. In particular, the latter predicts the labels of masked motifs and words, leveraging insights from each other, thereby enabling FineMolTex to understand the fine-grained matching between motifs and words. Finally, we conduct extensive experiments across three downstream tasks, achieving up to 230% improvement in the text-based molecule editing task. Additionally, our case studies reveal that FineMolTex successfully captures fine-grained knowledge, potentially offering valuable insights for drug discovery and catalyst design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14106v2-abstract-full').style.display = 'none'; document.getElementById('2409.14106v2-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">v1</span> submitted 21 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.12394">arXiv:2409.12394</a> <span> [<a href="https://arxiv.org/pdf/2409.12394">pdf</a>, <a href="https://arxiv.org/format/2409.12394">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"> ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shuai Yuan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongwei Li</a>, <a href="/search/cs?searchtype=author&query=Han%2C+X">Xingshuo Han</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+G">Guowen Xu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wenbo Jiang</a>, <a href="/search/cs?searchtype=author&query=Ni%2C+T">Tao Ni</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Q">Qingchuan Zhao</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuguang Fang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.12394v1-abstract-short" style="display: inline;"> Physical adversarial patches have emerged as a key adversarial attack to cause misclassification of traffic sign recognition (TSR) systems in the real world. However, existing adversarial patches have poor stealthiness and attack all vehicles indiscriminately once deployed. In this paper, we introduce an invisible and triggered physical adversarial patch (ITPatch) with a novel attack vector, i.e.,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12394v1-abstract-full').style.display = 'inline'; document.getElementById('2409.12394v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12394v1-abstract-full" style="display: none;"> Physical adversarial patches have emerged as a key adversarial attack to cause misclassification of traffic sign recognition (TSR) systems in the real world. However, existing adversarial patches have poor stealthiness and attack all vehicles indiscriminately once deployed. In this paper, we introduce an invisible and triggered physical adversarial patch (ITPatch) with a novel attack vector, i.e., fluorescent ink, to advance the state-of-the-art. It applies carefully designed fluorescent perturbations to a target sign, an attacker can later trigger a fluorescent effect using invisible ultraviolet light, causing the TSR system to misclassify the sign and potentially resulting in traffic accidents. We conducted a comprehensive evaluation to investigate the effectiveness of ITPatch, which shows a success rate of 98.31% in low-light conditions. Furthermore, our attack successfully bypasses five popular defenses and achieves a success rate of 96.72%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12394v1-abstract-full').style.display = 'none'; document.getElementById('2409.12394v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.10849">arXiv:2409.10849</a> <span> [<a href="https://arxiv.org/pdf/2409.10849">pdf</a>, <a href="https://arxiv.org/format/2409.10849">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> SIFToM: Robust Spoken Instruction Following through Theory of Mind </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ying%2C+L">Lance Ying</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+X">Jason Xinyu Liu</a>, <a href="/search/cs?searchtype=author&query=Aarya%2C+S">Shivam Aarya</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yizirui Fang</a>, <a href="/search/cs?searchtype=author&query=Tellex%2C+S">Stefanie Tellex</a>, <a href="/search/cs?searchtype=author&query=Tenenbaum%2C+J+B">Joshua B. Tenenbaum</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+T">Tianmin Shu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.10849v1-abstract-short" style="display: inline;"> Spoken language instructions are ubiquitous in agent collaboration. However, in human-robot collaboration, recognition accuracy for human speech is often influenced by various speech and environmental factors, such as background noise, the speaker's accents, and mispronunciation. When faced with noisy or unfamiliar auditory inputs, humans use context and prior knowledge to disambiguate the stimulu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10849v1-abstract-full').style.display = 'inline'; document.getElementById('2409.10849v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.10849v1-abstract-full" style="display: none;"> Spoken language instructions are ubiquitous in agent collaboration. However, in human-robot collaboration, recognition accuracy for human speech is often influenced by various speech and environmental factors, such as background noise, the speaker's accents, and mispronunciation. When faced with noisy or unfamiliar auditory inputs, humans use context and prior knowledge to disambiguate the stimulus and take pragmatic actions, a process referred to as top-down processing in cognitive science. We present a cognitively inspired model, Speech Instruction Following through Theory of Mind (SIFToM), to enable robots to pragmatically follow human instructions under diverse speech conditions by inferring the human's goal and joint plan as prior for speech perception and understanding. We test SIFToM in simulated home experiments (VirtualHome 2). Results show that the SIFToM model outperforms state-of-the-art speech and language models, approaching human-level accuracy on challenging speech instruction following tasks. We then demonstrate its ability at the task planning level on a mobile manipulator for breakfast preparation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10849v1-abstract-full').style.display = 'none'; document.getElementById('2409.10849v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 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/2409.10172">arXiv:2409.10172</a> <span> [<a href="https://arxiv.org/pdf/2409.10172">pdf</a>, <a href="https://arxiv.org/format/2409.10172">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> LiLoc: Lifelong Localization using Adaptive Submap Joining and Egocentric Factor Graph </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yixin Fang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanyan Li</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+K">Kun Qian</a>, <a href="/search/cs?searchtype=author&query=Tombari%2C+F">Federico Tombari</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yue Wang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+G+H">Gim Hee Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.10172v1-abstract-short" style="display: inline;"> This paper proposes a versatile graph-based lifelong localization framework, LiLoc, which enhances its timeliness by maintaining a single central session while improves the accuracy through multi-modal factors between the central and subsidiary sessions. First, an adaptive submap joining strategy is employed to generate prior submaps (keyframes and poses) for the central session, and to provide pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10172v1-abstract-full').style.display = 'inline'; document.getElementById('2409.10172v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.10172v1-abstract-full" style="display: none;"> This paper proposes a versatile graph-based lifelong localization framework, LiLoc, which enhances its timeliness by maintaining a single central session while improves the accuracy through multi-modal factors between the central and subsidiary sessions. First, an adaptive submap joining strategy is employed to generate prior submaps (keyframes and poses) for the central session, and to provide priors for subsidiaries when constraints are needed for robust localization. Next, a coarse-to-fine pose initialization for subsidiary sessions is performed using vertical recognition and ICP refinement in the global coordinate frame. To elevate the accuracy of subsequent localization, we propose an egocentric factor graph (EFG) module that integrates the IMU preintegration, LiDAR odometry and scan match factors in a joint optimization manner. Specifically, the scan match factors are constructed by a novel propagation model that efficiently distributes the prior constrains as edges to the relevant prior pose nodes, weighted by noises based on keyframe registration errors. Additionally, the framework supports flexible switching between two modes: relocalization (RLM) and incremental localization (ILM) based on the proposed overlap-based mechanism to select or update the prior submaps from central session. The proposed LiLoc is tested on public and custom datasets, demonstrating accurate localization performance against state-of-the-art methods. Our codes will be publicly available on https://github.com/Yixin-F/LiLoc. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10172v1-abstract-full').style.display = 'none'; document.getElementById('2409.10172v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09921">arXiv:2409.09921</a> <span> [<a href="https://arxiv.org/pdf/2409.09921">pdf</a>, <a href="https://arxiv.org/format/2409.09921">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Towards Real-Time Generation of Delay-Compensated Video Feeds for Outdoor Mobile Robot Teleoperation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chakraborty%2C+N">Neeloy Chakraborty</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yixiao Fang</a>, <a href="/search/cs?searchtype=author&query=Schreiber%2C+A">Andre Schreiber</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+T">Tianchen Ji</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhe Huang</a>, <a href="/search/cs?searchtype=author&query=Mihigo%2C+A">Aganze Mihigo</a>, <a href="/search/cs?searchtype=author&query=Wall%2C+C">Cassidy Wall</a>, <a href="/search/cs?searchtype=author&query=Almana%2C+A">Abdulrahman Almana</a>, <a href="/search/cs?searchtype=author&query=Driggs-Campbell%2C+K">Katherine Driggs-Campbell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.09921v1-abstract-short" style="display: inline;"> Teleoperation is an important technology to enable supervisors to control agricultural robots remotely. However, environmental factors in dense crop rows and limitations in network infrastructure hinder the reliability of data streamed to teleoperators. These issues result in delayed and variable frame rate video feeds that often deviate significantly from the robot's actual viewpoint. We propose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09921v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09921v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09921v1-abstract-full" style="display: none;"> Teleoperation is an important technology to enable supervisors to control agricultural robots remotely. However, environmental factors in dense crop rows and limitations in network infrastructure hinder the reliability of data streamed to teleoperators. These issues result in delayed and variable frame rate video feeds that often deviate significantly from the robot's actual viewpoint. We propose a modular learning-based vision pipeline to generate delay-compensated images in real-time for supervisors. Our extensive offline evaluations demonstrate that our method generates more accurate images compared to state-of-the-art approaches in our setting. Additionally, we are one of the few works to evaluate a delay-compensation method in outdoor field environments with complex terrain on data from a real robot in real-time. Additional videos are provided at https://sites.google.com/illinois.edu/comp-teleop. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09921v1-abstract-full').style.display = 'none'; document.getElementById('2409.09921v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 4 figures, 3 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/2409.09417">arXiv:2409.09417</a> <span> [<a href="https://arxiv.org/pdf/2409.09417">pdf</a>, <a href="https://arxiv.org/format/2409.09417">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Resources on the Move for Smart City: A Disruptive Perspective on the Grand Convergence of Sensing, Communications, Computing, Storage, and Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yuguang Fang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Yiqin Deng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xianhao Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.09417v2-abstract-short" style="display: inline;"> The most commonly seen things on streets in any city are vehicles. However, most of them are used to transport people or goods. What if they also carry resources and capabilities for sensing, communications, computing, storage, and intelligence (SCCSI)? We will have a web of sensors to monitor the city, a network of powerful communicators to transport data around, a grid of computing power to cond… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09417v2-abstract-full').style.display = 'inline'; document.getElementById('2409.09417v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09417v2-abstract-full" style="display: none;"> The most commonly seen things on streets in any city are vehicles. However, most of them are used to transport people or goods. What if they also carry resources and capabilities for sensing, communications, computing, storage, and intelligence (SCCSI)? We will have a web of sensors to monitor the city, a network of powerful communicators to transport data around, a grid of computing power to conduct data analytics and machine learning (ML), a network of distributed storage to buffer/cache data/job for optimization, and a set of movable AI/ML toolboxes made available for specialized smart applications. This perspective article presents how to leverage SCCSI-empowered vehicles to design such a service network, simply called SCCSI network, to help build a smart city with a cost-effective and sustainable solution. It showcases how multi-dimensional technologies, namely, sensing, communications, computing, storage, and intelligence, converge to a unifying technology to solve grand challenges for resource demands from emerging large-scale applications. Thus, with SCCSI-empowered vehicles on the ground, over the air, and on the sea, SCCSI network can make resources and capabilities on the move, practically pushing SCCSI services to the edge! We hope this article serves as a spark to stimulate more disruptive thinking to address grand challenges of paramount importance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09417v2-abstract-full').style.display = 'none'; document.getElementById('2409.09417v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 3 figures. Accepted by IEEE Communications Magazine</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08859">arXiv:2409.08859</a> <span> [<a href="https://arxiv.org/pdf/2409.08859">pdf</a>, <a href="https://arxiv.org/format/2409.08859">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Optimized Design of A Haptic Unit for Vibrotactile Amplitude Modulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jingchen Huang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yun Fang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+W">Weichao Guo</a>, <a href="/search/cs?searchtype=author&query=Sheng%2C+X">Xinjun Sheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.08859v1-abstract-short" style="display: inline;"> Communicating information to users is a crucial aspect of human-machine interaction. Vibrotactile feedback encodes information into spatiotemporal vibrations, enabling users to perceive tactile sensations. It offers advantages such as lightweight, wearability, and high stability, with broad applications in sensory substitution, virtual reality, education, and healthcare. However, existing haptic u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08859v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08859v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08859v1-abstract-full" style="display: none;"> Communicating information to users is a crucial aspect of human-machine interaction. Vibrotactile feedback encodes information into spatiotemporal vibrations, enabling users to perceive tactile sensations. It offers advantages such as lightweight, wearability, and high stability, with broad applications in sensory substitution, virtual reality, education, and healthcare. However, existing haptic unit designs lack amplitude modulation capabilities, which limits their applications. This paper proposed an optimized design of the haptic unit from the perspective of vibration amplitude modulation. A modified elastic model was developed to describe the propagation and attenuation mechanisms of vibration in the skin. Based on the model, two types of hierarchical architectural design were proposed. The design incorporated various materials arranged in multiple layers to amplify or attenuate the vibration amplitude as it traveled through the structure. An experimental platform was built to evaluate the performance of the optimized design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08859v1-abstract-full').style.display = 'none'; document.getElementById('2409.08859v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Fang%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository