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 104 results for author: <span class="mathjax">Lei, H</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=Lei%2C+H">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="Lei, H"> </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=Lei%2C+H&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="Lei, H"> <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=Lei%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12188">arXiv:2502.12188</a> <span> [<a href="https://arxiv.org/pdf/2502.12188">pdf</a>, <a href="https://arxiv.org/format/2502.12188">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"> Boosting Generalization in Diffusion-Based Neural Combinatorial Solver via Energy-guided Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haoyu Lei</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+K">Kaiwen Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinchuan Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhitang Chen</a>, <a href="/search/cs?searchtype=author&query=Farnia%2C+F">Farzan Farnia</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="2502.12188v1-abstract-short" style="display: inline;"> Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12188v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12188v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12188v1-abstract-full" style="display: none;"> Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditional solvers. While recent studies have introduced training-free guidance approaches that leverage pre-defined guidance functions for zero-shot conditional generation, such methodologies have not been extensively explored in combinatorial optimization. To bridge this gap, we propose a general energy-guided sampling framework during inference time that enhances both the cross-scale and cross-problem generalization capabilities of diffusion-based NCO solvers without requiring additional training. We provide theoretical analysis that helps understanding the cross-problem transfer capability. Our experimental results demonstrate that a diffusion solver, trained exclusively on the Traveling Salesman Problem (TSP), can achieve competitive zero-shot solution generation on TSP variants, such as Prize Collecting TSP (PCTSP) and the Orienteering Problem (OP), through energy-guided sampling across different problem scales. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12188v1-abstract-full').style.display = 'none'; document.getElementById('2502.12188v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11375">arXiv:2502.11375</a> <span> [<a href="https://arxiv.org/pdf/2502.11375">pdf</a>, <a href="https://arxiv.org/format/2502.11375">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Robot Deformable Object Manipulation via NMPC-generated Demonstrations in Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haoyuan Wang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Z">Zihao Dong</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongliang Lei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zejia Zhang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+W">Weizhuang Shi</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+W">Wei Luo</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+W">Weiwei Wan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jian 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="2502.11375v1-abstract-short" style="display: inline;"> In this work, we conducted research on deformable object manipulation by robots based on demonstration-enhanced reinforcement learning (RL). To improve the learning efficiency of RL, we enhanced the utilization of demonstration data from multiple aspects and proposed the HGCR-DDPG algorithm. It uses a novel high-dimensional fuzzy approach for grasping-point selection, a refined behavior-cloning me… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11375v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11375v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11375v1-abstract-full" style="display: none;"> In this work, we conducted research on deformable object manipulation by robots based on demonstration-enhanced reinforcement learning (RL). To improve the learning efficiency of RL, we enhanced the utilization of demonstration data from multiple aspects and proposed the HGCR-DDPG algorithm. It uses a novel high-dimensional fuzzy approach for grasping-point selection, a refined behavior-cloning method to enhance data-driven learning in Rainbow-DDPG, and a sequential policy-learning strategy. Compared to the baseline algorithm (Rainbow-DDPG), our proposed HGCR-DDPG achieved 2.01 times the global average reward and reduced the global average standard deviation to 45% of that of the baseline algorithm. To reduce the human labor cost of demonstration collection, we proposed a low-cost demonstration collection method based on Nonlinear Model Predictive Control (NMPC). Simulation experiment results show that demonstrations collected through NMPC can be used to train HGCR-DDPG, achieving comparable results to those obtained with human demonstrations. To validate the feasibility of our proposed methods in real-world environments, we conducted physical experiments involving deformable object manipulation. We manipulated fabric to perform three tasks: diagonal folding, central axis folding, and flattening. The experimental results demonstrate that our proposed method achieved success rates of 83.3%, 80%, and 100% for these three tasks, respectively, validating the effectiveness of our approach. Compared to current large-model approaches for robot manipulation, the proposed algorithm is lightweight, requires fewer computational resources, and offers task-specific customization and efficient adaptability for specific tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11375v1-abstract-full').style.display = 'none'; document.getElementById('2502.11375v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15553">arXiv:2501.15553</a> <span> [<a href="https://arxiv.org/pdf/2501.15553">pdf</a>, <a href="https://arxiv.org/format/2501.15553">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Real-CATS: A Practical Training Ground for Emerging Research on Cryptocurrency Cybercrime Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jiadong Shi</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+C">Chunyu Duan</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hao Lei</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liangmin 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="2501.15553v1-abstract-short" style="display: inline;"> Cybercriminals pose a significant threat to blockchain trading security, causing $40.9 billion in losses in 2024. However, the lack of an effective real-world address dataset hinders the advancement of cybercrime detection research. The anti-cybercrime efforts of researchers from broader fields, such as statistics and artificial intelligence, are blocked by data scarcity. In this paper, we present… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15553v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15553v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15553v1-abstract-full" style="display: none;"> Cybercriminals pose a significant threat to blockchain trading security, causing $40.9 billion in losses in 2024. However, the lack of an effective real-world address dataset hinders the advancement of cybercrime detection research. The anti-cybercrime efforts of researchers from broader fields, such as statistics and artificial intelligence, are blocked by data scarcity. In this paper, we present Real-CATS, a Real-world dataset of Cryptocurrency Addresses with Transaction profileS, serving as a practical training ground for developing and assessing detection methods. Real-CATS comprises 103,203 criminal addresses from real-world reports and 106,196 benign addresses from exchange customers. It satifies the C3R characteristics (Comprehensiveness, Classifiability, Customizability, and Real-world Transferability), which are fundemental for practical detection of cryptocurrency cybercrime. The dataset provides three main functions: 1) effective evaluation of detection methods, 2) support for feature extensions, and 3) a new evaluation scenario for real-world deployment. Real-CATS also offers opportunities to expand cybercrime measurement studies. It is particularly beneficial for researchers without cryptocurrency-related knowledge to engage in this emerging research field. We hope that studies on cryptocurrency cybercrime detection will be promoted by an increasing number of cross-disciplinary researchers drawn to this versatile data platform. All datasets are available at https://github.com/sjdseu/Real-CATS <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15553v1-abstract-full').style.display = 'none'; document.getElementById('2501.15553v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </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, 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/2412.16615">arXiv:2412.16615</a> <span> [<a href="https://arxiv.org/pdf/2412.16615">pdf</a>, <a href="https://arxiv.org/format/2412.16615">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ji%2C+L">Luo Ji</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+F">Feixiang Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Teng Chen</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Q">Qingqing Gu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaoyu Wang</a>, <a href="/search/cs?searchtype=author&query=Xi%2C+N">Ningyuan Xi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yihong Wang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P">Peng Yu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yue Zhao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongyang Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhonglin Jiang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yong 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="2412.16615v1-abstract-short" style="display: inline;"> Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and positive documents are semantically similar. In this paper, we instead propose and study a more challenging type of retrieval task, called hidden rationale retrieval, in which query and document are not similar but can be in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16615v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16615v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16615v1-abstract-full" style="display: none;"> Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and positive documents are semantically similar. In this paper, we instead propose and study a more challenging type of retrieval task, called hidden rationale retrieval, in which query and document are not similar but can be inferred by reasoning chains, logic relationships, or empirical experiences. To address such problems, an instruction-tuned Large language model (LLM) with a cross-encoder architecture could be a reasonable choice. To further strengthen pioneering LLM-based retrievers, we design a special instruction that transforms the retrieval task into a generative task by prompting LLM to answer a binary-choice question. The model can be fine-tuned with direct preference optimization (DPO). The framework is also optimized for computational efficiency with no performance degradation. We name this retrieval framework by RaHoRe and verify its zero-shot and fine-tuned performance superiority on Emotional Support Conversation (ESC), compared with previous retrieval works. Our study suggests the potential to employ LLM as a foundation for a wider scope of retrieval tasks. Our codes, models, and datasets are available on https://github.com/flyfree5/LaHoRe. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16615v1-abstract-full').style.display = 'none'; document.getElementById('2412.16615v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 3 figures, accepted by ECIR 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/2412.13502">arXiv:2412.13502</a> <span> [<a href="https://arxiv.org/pdf/2412.13502">pdf</a>, <a href="https://arxiv.org/format/2412.13502">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"> Level-Set Parameters: Novel Representation for 3D Shape Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huan Lei</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongdong Li</a>, <a href="/search/cs?searchtype=author&query=Geiger%2C+A">Andreas Geiger</a>, <a href="/search/cs?searchtype=author&query=Dick%2C+A">Anthony Dick</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.13502v1-abstract-short" style="display: inline;"> 3D shape analysis has been largely focused on traditional 3D representations of point clouds and meshes, but the discrete nature of these data makes the analysis susceptible to variations in input resolutions. Recent development of neural fields brings in level-set parameters from signed distance functions as a novel, continuous, and numerical representation of 3D shapes, where the shape surfaces… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13502v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13502v1-abstract-full" style="display: none;"> 3D shape analysis has been largely focused on traditional 3D representations of point clouds and meshes, but the discrete nature of these data makes the analysis susceptible to variations in input resolutions. Recent development of neural fields brings in level-set parameters from signed distance functions as a novel, continuous, and numerical representation of 3D shapes, where the shape surfaces are defined as zero-level-sets of those functions. This motivates us to extend shape analysis from the traditional 3D data to these novel parameter data. Since the level-set parameters are not Euclidean like point clouds, we establish correlations across different shapes by formulating them as a pseudo-normal distribution, and learn the distribution prior from the respective dataset. To further explore the level-set parameters with shape transformations, we propose to condition a subset of these parameters on rotations and translations, and generate them with a hypernetwork. This simplifies the pose-related shape analysis compared to using traditional data. We demonstrate the promise of the novel representations through applications in shape classification (arbitrary poses), retrieval, and 6D object pose estimation. Code and data in this research are provided at https://github.com/EnyaHermite/LevelSetParamData. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13502v1-abstract-full').style.display = 'none'; document.getElementById('2412.13502v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.01476">arXiv:2412.01476</a> <span> [<a href="https://arxiv.org/pdf/2412.01476">pdf</a>, <a href="https://arxiv.org/format/2412.01476">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"> ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+R">RuiZhe Jiang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haotian Lei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.01476v2-abstract-short" style="display: inline;"> Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques tailored to various tasks and model architectures. In this paper, we introduce a simple perspective on overfitting: models learn different representations in diff… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01476v2-abstract-full').style.display = 'inline'; document.getElementById('2412.01476v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01476v2-abstract-full" style="display: none;"> Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques tailored to various tasks and model architectures. In this paper, we introduce a simple perspective on overfitting: models learn different representations in different i.i.d. datasets. Based on this viewpoint, we propose an adaptive method, ConsistentFeature, that regularizes the model by constraining feature differences across random subsets of the same training set. Due to minimal prior assumptions, this approach is applicable to almost any architecture and task. Our experiments show that it effectively reduces overfitting, with low sensitivity to hyperparameters and minimal computational cost. It demonstrates particularly strong memory suppression and promotes normal convergence, even when the model has already started to overfit. Even in the absence of significant overfitting, our method consistently improves accuracy and reduces validation loss. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01476v2-abstract-full').style.display = 'none'; document.getElementById('2412.01476v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.01029">arXiv:2412.01029</a> <span> [<a href="https://arxiv.org/pdf/2412.01029">pdf</a>, <a href="https://arxiv.org/ps/2412.01029">ps</a>, <a href="https://arxiv.org/format/2412.01029">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning Based Near-Field User Localization with Beam Squint in Wideband XL-MIMO Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hao Lei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiayi Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+H">Huahua Xiao</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+D+W+K">Derrick Wing Kwan Ng</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+B">Bo Ai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.01029v1-abstract-short" style="display: inline;"> Extremely large-scale multiple-input multiple-output (XL-MIMO) is gaining attention as a prominent technology for enabling the sixth-generation (6G) wireless networks. However, the vast antenna array and the huge bandwidth introduce a non-negligible beam squint effect, causing beams of different frequencies to focus at different locations. One approach to cope with this is to employ true-time-dela… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01029v1-abstract-full').style.display = 'inline'; document.getElementById('2412.01029v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01029v1-abstract-full" style="display: none;"> Extremely large-scale multiple-input multiple-output (XL-MIMO) is gaining attention as a prominent technology for enabling the sixth-generation (6G) wireless networks. However, the vast antenna array and the huge bandwidth introduce a non-negligible beam squint effect, causing beams of different frequencies to focus at different locations. One approach to cope with this is to employ true-time-delay lines (TTDs)-based beamforming to control the range and trajectory of near-field beam squint, known as the near-field controllable beam squint (CBS) effect. In this paper, we investigate the user localization in near-field wideband XL-MIMO systems under the beam squint effect and spatial non-stationary properties. Firstly, we derive the expressions for Cram茅r-Rao Bounds (CRBs) for characterizing the performance of estimating both angle and distance. This analysis aims to assess the potential of leveraging CBS for precise user localization. Secondly, a user localization scheme combining CBS and beam training is proposed. Specifically, we organize multiple subcarriers into groups, directing beams from different groups to distinct angles or distances through the CBS to obtain the estimates of users' angles and distances. Furthermore, we design a user localization scheme based on a convolutional neural network model, namely ConvNeXt. This scheme utilizes the inputs and outputs of the CBS-based scheme to generate high-precision estimates of angle and distance. More importantly, our proposed ConvNeXt-based user localization scheme achieves centimeter-level accuracy in localization estimates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01029v1-abstract-full').style.display = 'none'; document.getElementById('2412.01029v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02653">arXiv:2411.02653</a> <span> [<a href="https://arxiv.org/pdf/2411.02653">pdf</a>, <a href="https://arxiv.org/format/2411.02653">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Earth and Planetary Astrophysics">astro-ph.EP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Methods for Astrophysics">astro-ph.IM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</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/10.1051/0004-6361/202451789">10.1051/0004-6361/202451789 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Deep operator neural network applied to efficient computation of asteroid surface temperature and the Yarkovsky effect </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shunjing Zhao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hanlun Lei</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xian Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02653v1-abstract-short" style="display: inline;"> Surface temperature distribution is crucial for thermal property-based studies about irregular asteroids in our Solar System. While direct numerical simulations could model surface temperatures with high fidelity, they often take a significant amount of computational time, especially for problems where temperature distributions are required to be repeatedly calculated. To this end, deep operator n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02653v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02653v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02653v1-abstract-full" style="display: none;"> Surface temperature distribution is crucial for thermal property-based studies about irregular asteroids in our Solar System. While direct numerical simulations could model surface temperatures with high fidelity, they often take a significant amount of computational time, especially for problems where temperature distributions are required to be repeatedly calculated. To this end, deep operator neural network (DeepONet) provides a powerful tool due to its high computational efficiency and generalization ability. In this work, we applied DeepONet to the modelling of asteroid surface temperatures. Results show that the trained network is able to predict temperature with an accuracy of ~1% on average, while the computational cost is five orders of magnitude lower, hence enabling thermal property analysis in a multidimensional parameter space. As a preliminary application, we analyzed the orbital evolution of asteroids through direct N-body simulations embedded with instantaneous Yarkovsky effect inferred by DeepONet-based thermophysical modelling.Taking asteroids (3200) Phaethon and (89433) 2001 WM41 as examples, we show the efficacy and efficiency of our AI-based approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02653v1-abstract-full').style.display = 'none'; document.getElementById('2411.02653v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted for publication in "Astronomy & Astrophysics"</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00217">arXiv:2411.00217</a> <span> [<a href="https://arxiv.org/pdf/2411.00217">pdf</a>, <a href="https://arxiv.org/format/2411.00217">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> ADAPT: A Game-Theoretic and Neuro-Symbolic Framework for Automated Distributed Adaptive Penetration Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+Y">Yunfei Ge</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan 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="2411.00217v1-abstract-short" style="display: inline;"> The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made traditional human-driven penetration testing insufficient for assessing risks and developing remediation strategies. Consequently, there is a pressing need for a di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00217v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00217v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00217v1-abstract-full" style="display: none;"> The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made traditional human-driven penetration testing insufficient for assessing risks and developing remediation strategies. Consequently, there is a pressing need for a distributed, adaptive, and efficient automated penetration testing framework that not only identifies vulnerabilities but also provides countermeasures to enhance security posture. This work presents ADAPT, a game-theoretic and neuro-symbolic framework for automated distributed adaptive penetration testing, specifically designed to address the unique cybersecurity challenges of AI-enabled healthcare infrastructure networks. We use a healthcare system case study to illustrate the methodologies within ADAPT. The proposed solution enables a learning-based risk assessment. Numerical experiments are used to demonstrate effective countermeasures against various tactical techniques employed by adversarial AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00217v1-abstract-full').style.display = 'none'; document.getElementById('2411.00217v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04225">arXiv:2410.04225</a> <span> [<a href="https://arxiv.org/pdf/2410.04225">pdf</a>, <a href="https://arxiv.org/format/2410.04225">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="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Molodetskikh%2C+I">Ivan Molodetskikh</a>, <a href="/search/cs?searchtype=author&query=Borisov%2C+A">Artem Borisov</a>, <a href="/search/cs?searchtype=author&query=Vatolin%2C+D">Dmitriy Vatolin</a>, <a href="/search/cs?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jianzhao Liu</a>, <a href="/search/cs?searchtype=author&query=Zhi%2C+T">Tianwu Zhi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yabin Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jingwen Xu</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+Y">Yiting Liao</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Q">Qing Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Ao-Xiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Peng Zhang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haibo Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+L">Linyan Jiang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yaqing Li</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuqin Cao</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Wei Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weixia Zhang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yinan Sun</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+Z">Ziheng Jia</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuxin Zhu</a>, <a href="/search/cs?searchtype=author&query=Min%2C+X">Xiongkuo Min</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+G">Guangtao Zhai</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+W">Weihua Luo</a> , et al. (2 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="2410.04225v1-abstract-short" style="display: inline;"> This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04225v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04225v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04225v1-abstract-full" style="display: none;"> This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjective scores collected from >150,000 pairwise votes obtained through crowd-sourced comparisons across 52 SR methods and 1124 upscaled videos. The goal was to advance the state-of-the-art in SR QA, which had proven to be a challenging problem with limited applicability of traditional QA methods. The challenge had 29 registered participants, and 5 teams had submitted their final results, all outperforming the current state-of-the-art. All data, including the private test subset, has been made publicly available on the challenge homepage at https://challenges.videoprocessing.ai/challenges/super-resolution-metrics-challenge.html <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04225v1-abstract-full').style.display = 'none'; document.getElementById('2410.04225v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 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/2409.08579">arXiv:2409.08579</a> <span> [<a href="https://arxiv.org/pdf/2409.08579">pdf</a>, <a href="https://arxiv.org/ps/2409.08579">ps</a>, <a href="https://arxiv.org/format/2409.08579">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> </div> </div> <p class="title is-5 mathjax"> Secure Offloading in NOMA-Aided Aerial MEC Systems Based on Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Mingxu Yang</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng 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="2409.08579v2-abstract-short" style="display: inline;"> Mobile edge computing (MEC) technology can reduce user latency and energy consumption by offloading computationally intensive tasks to the edge servers. Unmanned aerial vehicles (UAVs) and non-orthogonal multiple access (NOMA) technology enable the MEC networks to provide offloaded computing services for massively accessed terrestrial users conveniently. However, the broadcast nature of signal pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08579v2-abstract-full').style.display = 'inline'; document.getElementById('2409.08579v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08579v2-abstract-full" style="display: none;"> Mobile edge computing (MEC) technology can reduce user latency and energy consumption by offloading computationally intensive tasks to the edge servers. Unmanned aerial vehicles (UAVs) and non-orthogonal multiple access (NOMA) technology enable the MEC networks to provide offloaded computing services for massively accessed terrestrial users conveniently. However, the broadcast nature of signal propagation in NOMA-based UAV-MEC networks makes it vulnerable to eavesdropping by malicious eavesdroppers. In this work, a secure offload scheme is proposed for NOMA-based UAV-MEC systems with the existence of an aerial eavesdropper. The long-term average network computational cost is minimized by jointly designing the UAV's trajectory, the terrestrial users' transmit power, and computational frequency while ensuring the security of users' offloaded data. Due to the eavesdropper's location uncertainty, the worst-case security scenario is considered through the estimated eavesdropping range. Due to the high-dimensional continuous action space, the deep deterministic policy gradient algorithm is utilized to solve the non-convex optimization problem. Simulation results validate the effectiveness of the proposed scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08579v2-abstract-full').style.display = 'none'; document.getElementById('2409.08579v2-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">v1</span> submitted 13 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">12 pages, 7 figures, accepted by IEEE Journal on Miniaturization for Air and Space Systems</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07680">arXiv:2409.07680</a> <span> [<a href="https://arxiv.org/pdf/2409.07680">pdf</a>, <a href="https://arxiv.org/ps/2409.07680">ps</a>, <a href="https://arxiv.org/format/2409.07680">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Discrete Mathematics">cs.DM</span> </div> </div> <p class="title is-5 mathjax"> Upper bounds on minimum size of feedback arc set of directed multigraphs with bounded degree </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gutin%2C+G">Gregory Gutin</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hui Lei</a>, <a href="/search/cs?searchtype=author&query=Yeo%2C+A">Anders Yeo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yacong Zhou</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="2409.07680v1-abstract-short" style="display: inline;"> An oriented multigraph is a directed multigraph without directed 2-cycles. Let ${\rm fas}(D)$ denote the minimum size of a feedback arc set in an oriented multigraph $D$. The degree of a vertex is the sum of its out- and in-degrees. In several papers, upper bounds for ${\rm fas}(D)$ were obtained for oriented multigraphs $D$ with maximum degree upper-bounded by a constant. Hanauer (2017) conjectur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07680v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07680v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07680v1-abstract-full" style="display: none;"> An oriented multigraph is a directed multigraph without directed 2-cycles. Let ${\rm fas}(D)$ denote the minimum size of a feedback arc set in an oriented multigraph $D$. The degree of a vertex is the sum of its out- and in-degrees. In several papers, upper bounds for ${\rm fas}(D)$ were obtained for oriented multigraphs $D$ with maximum degree upper-bounded by a constant. Hanauer (2017) conjectured that ${\rm fas}(D)\le 2.5n/3$ for every oriented multigraph $D$ with $n$ vertices and maximum degree at most 5. We prove a strengthening of the conjecture: ${\rm fas}(D)\le m/3$ holds for every oriented multigraph $D$ with $m$ arcs and maximum degree at most 5. This bound is tight and improves a bound of Berger and Shor (1990,1997). It would be interesting to determine $c$ such that ${\rm fas}(D)\le cn$ for every oriented multigraph $D$ with $n$ vertices and maximum degree at most 5 such that the bound is tight. We show that $\frac{5}{7}\le c \le \frac{24}{29} < \frac{2.5}{3}$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07680v1-abstract-full').style.display = 'none'; document.getElementById('2409.07680v1-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 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/2409.06601">arXiv:2409.06601</a> <span> [<a href="https://arxiv.org/pdf/2409.06601">pdf</a>, <a href="https://arxiv.org/format/2409.06601">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Alleviating Hallucinations in Large Language Models with Scepticism Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yetao Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yihong Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Teng Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chenxi Liu</a>, <a href="/search/cs?searchtype=author&query=Xi%2C+N">Ningyuan Xi</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Q">Qingqing Gu</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongyang Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhonglin Jiang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yong Chen</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+L">Luo Ji</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="2409.06601v1-abstract-short" style="display: inline;"> Hallucinations is a major challenge for large language models (LLMs), prevents adoption in diverse fields. Uncertainty estimation could be used for alleviating the damages of hallucinations. The skeptical emotion of human could be useful for enhancing the ability of self estimation. Inspirited by this observation, we proposed a new approach called Skepticism Modeling (SM). This approach is formali… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06601v1-abstract-full').style.display = 'inline'; document.getElementById('2409.06601v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.06601v1-abstract-full" style="display: none;"> Hallucinations is a major challenge for large language models (LLMs), prevents adoption in diverse fields. Uncertainty estimation could be used for alleviating the damages of hallucinations. The skeptical emotion of human could be useful for enhancing the ability of self estimation. Inspirited by this observation, we proposed a new approach called Skepticism Modeling (SM). This approach is formalized by combining the information of token and logits for self estimation. We construct the doubt emotion aware data, perform continual pre-training, and then fine-tune the LLMs, improve their ability of self estimation. Experimental results demonstrate this new approach effectively enhances a model's ability to estimate their uncertainty, and validate its generalization ability of other tasks by out-of-domain experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06601v1-abstract-full').style.display = 'none'; document.getElementById('2409.06601v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 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">11 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05929">arXiv:2409.05929</a> <span> [<a href="https://arxiv.org/pdf/2409.05929">pdf</a>, <a href="https://arxiv.org/format/2409.05929">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"> Alt-MoE:A Scalable Framework for Bidirectional Multimodal Alignment and Efficient Knowledge Integration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongyang Lei</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xiaolong Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Dan Wang</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+K">Kun Fan</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+Q">Qi Qin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Huazhen Huang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yetao Wu</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Q">Qingqing Gu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhonglin Jiang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yong Chen</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+L">Luo Ji</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="2409.05929v3-abstract-short" style="display: inline;"> Multimodal learning has advanced significantly by aligning different modalities within shared latent spaces, enabling tasks such as cross-modal understanding and generation. Current alignment strategies in multimodal learning primarily include direct alignment using pre-trained or unified encoders and single-directional alignment via modality-specific connectors. Direct alignment struggles to full… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05929v3-abstract-full').style.display = 'inline'; document.getElementById('2409.05929v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05929v3-abstract-full" style="display: none;"> Multimodal learning has advanced significantly by aligning different modalities within shared latent spaces, enabling tasks such as cross-modal understanding and generation. Current alignment strategies in multimodal learning primarily include direct alignment using pre-trained or unified encoders and single-directional alignment via modality-specific connectors. Direct alignment struggles to fully leverage rich intra-modal knowledge, often requiring extensive training data to achieve cross-modal representation. Meanwhile, single-directional alignment methods, despite leveraging pre-trained knowledge, restrict task adaptability and hinder the model's ability to capture bidirectional relationships, leading to incomplete knowledge fusion and underutilization of complementary modality-specific information. To address these limitations, we introduce Alt-MoE, a scalable multimodal alignment framework that employs a mixture of experts (MoE) model as a multi-directional connector across modalities. By utilizing a sequential alternating one-way alignment strategy, Alt-MoE iteratively refines the model to achieve bidirectional alignment. Alt-MoE operates in latent space, enabling efficient vector pre-storage and real-time retrieval via MoE, optimizing large-scale data processing. Extensive empirical studies demonstrate that Alt-MoE achieves competitive performance on cross-modal retrieval and visual question answering by integrating diverse modality-specific knowledge, generalizing to unseen data, and easily scaling to new tasks and modalities through dynamic adjustment of MoE capacity and expert activation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05929v3-abstract-full').style.display = 'none'; document.getElementById('2409.05929v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 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/2409.00243">arXiv:2409.00243</a> <span> [<a href="https://arxiv.org/pdf/2409.00243">pdf</a>, <a href="https://arxiv.org/format/2409.00243">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> PRADA: Proactive Risk Assessment and Mitigation of Misinformed Demand Attacks on Navigational Route Recommendations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ya-Ting Yang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan 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="2409.00243v1-abstract-short" style="display: inline;"> Leveraging recent advances in wireless communication, IoT, and AI, intelligent transportation systems (ITS) played an important role in reducing traffic congestion and enhancing user experience. Within ITS, navigational recommendation systems (NRS) are essential for helping users simplify route choices in urban environments. However, NRS are vulnerable to information-based attacks that can manipul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00243v1-abstract-full').style.display = 'inline'; document.getElementById('2409.00243v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00243v1-abstract-full" style="display: none;"> Leveraging recent advances in wireless communication, IoT, and AI, intelligent transportation systems (ITS) played an important role in reducing traffic congestion and enhancing user experience. Within ITS, navigational recommendation systems (NRS) are essential for helping users simplify route choices in urban environments. However, NRS are vulnerable to information-based attacks that can manipulate both the NRS and users to achieve the objectives of the malicious entities. This study aims to assess the risks of misinformed demand attacks, where attackers use techniques like Sybil-based attacks to manipulate the demands of certain origins and destinations considered by the NRS. We propose a game-theoretic framework for proactive risk assessment of demand attacks (PRADA) and treat the interaction between attackers and the NRS as a Stackelberg game. The attacker is the leader who conveys misinformed demands, while the NRS is the follower responding to the provided information. Specifically, we consider the case of local-targeted attacks, in which the attacker aims to make the NRS recommend the authentic users towards a specific road that favors certain groups. Our analysis unveils the equivalence between users' incentive compatibility and Wardrop equilibrium recommendations and shows that the NRS and its users are at high risk when encountering intelligent attackers who can significantly alter user routes by strategically fabricating non-existent demands. To mitigate these risks, we introduce a trust mechanism that leverages users' confidence in the integrity of the NRS, and show that it can effectively reduce the impact of misinformed demand attacks. Numerical experiments are used to corroborate the results and demonstrate a Resilience Paradox, where locally targeted attacks can sometimes benefit the overall traffic conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00243v1-abstract-full').style.display = 'none'; document.getElementById('2409.00243v1-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 August, 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/2409.00236">arXiv:2409.00236</a> <span> [<a href="https://arxiv.org/pdf/2409.00236">pdf</a>, <a href="https://arxiv.org/format/2409.00236">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Adaptive Incentive-Compatible Navigational Route Recommendations in Urban Transportation Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ya-Ting Yang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan 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="2409.00236v1-abstract-short" style="display: inline;"> In urban transportation environments, drivers often encounter various path (route) options when navigating to their destinations. This emphasizes the importance of navigational recommendation systems (NRS), which simplify decision-making and reduce travel time for users while alleviating potential congestion for broader societal benefits. However, recommending the shortest path may cause the flash… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00236v1-abstract-full').style.display = 'inline'; document.getElementById('2409.00236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00236v1-abstract-full" style="display: none;"> In urban transportation environments, drivers often encounter various path (route) options when navigating to their destinations. This emphasizes the importance of navigational recommendation systems (NRS), which simplify decision-making and reduce travel time for users while alleviating potential congestion for broader societal benefits. However, recommending the shortest path may cause the flash crowd effect, and system-optimal routes may not always align the preferences of human users, leading to non-compliance issues. It is also worth noting that universal NRS adoption is impractical. Therefore, in this study, we aim to address these challenges by proposing an incentive compatibility recommendation system from a game-theoretic perspective and accounts for non-user drivers with their own path choice behaviors. Additionally, recognizing the dynamic nature of traffic conditions and the unpredictability of accidents, this work introduces a dynamic NRS with parallel and random update schemes, enabling users to safely adapt to changing traffic conditions while ensuring optimal total travel time costs. The numerical studies indicate that the proposed parallel update scheme exhibits greater effectiveness in terms of user compliance, travel time reduction, and adaptability to the environment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00236v1-abstract-full').style.display = 'none'; document.getElementById('2409.00236v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.16451">arXiv:2408.16451</a> <span> [<a href="https://arxiv.org/pdf/2408.16451">pdf</a>, <a href="https://arxiv.org/format/2408.16451">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"> Weakly Supervised Object Detection for Automatic Tooth-marked Tongue Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongcun Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiajun Xu</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yina He</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shaozi Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Zhiming Luo</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huangwei Lei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.16451v1-abstract-short" style="display: inline;"> Tongue diagnosis in Traditional Chinese Medicine (TCM) is a crucial diagnostic method that can reflect an individual's health status. Traditional methods for identifying tooth-marked tongues are subjective and inconsistent because they rely on practitioner experience. We propose a novel fully automated Weakly Supervised method using Vision transformer and Multiple instance learning WSVM for tongue… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16451v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16451v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16451v1-abstract-full" style="display: none;"> Tongue diagnosis in Traditional Chinese Medicine (TCM) is a crucial diagnostic method that can reflect an individual's health status. Traditional methods for identifying tooth-marked tongues are subjective and inconsistent because they rely on practitioner experience. We propose a novel fully automated Weakly Supervised method using Vision transformer and Multiple instance learning WSVM for tongue extraction and tooth-marked tongue recognition. Our approach first accurately detects and extracts the tongue region from clinical images, removing any irrelevant background information. Then, we implement an end-to-end weakly supervised object detection method. We utilize Vision Transformer (ViT) to process tongue images in patches and employ multiple instance loss to identify tooth-marked regions with only image-level annotations. WSVM achieves high accuracy in tooth-marked tongue classification, and visualization experiments demonstrate its effectiveness in pinpointing these regions. This automated approach enhances the objectivity and accuracy of tooth-marked tongue diagnosis. It provides significant clinical value by assisting TCM practitioners in making precise diagnoses and treatment recommendations. Code is available at https://github.com/yc-zh/WSVM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16451v1-abstract-full').style.display = 'none'; document.getElementById('2408.16451v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.11982">arXiv:2408.11982</a> <span> [<a href="https://arxiv.org/pdf/2408.11982">pdf</a>, <a href="https://arxiv.org/format/2408.11982">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="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Smirnov%2C+M">Maksim Smirnov</a>, <a href="/search/cs?searchtype=author&query=Gushchin%2C+A">Aleksandr Gushchin</a>, <a href="/search/cs?searchtype=author&query=Antsiferova%2C+A">Anastasia Antsiferova</a>, <a href="/search/cs?searchtype=author&query=Vatolin%2C+D">Dmitry Vatolin</a>, <a href="/search/cs?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+Z">Ziheng Jia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zicheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Wei Sun</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+J">Jiaying Qian</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuqin Cao</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yinan Sun</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuxin Zhu</a>, <a href="/search/cs?searchtype=author&query=Min%2C+X">Xiongkuo Min</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+G">Guangtao Zhai</a>, <a href="/search/cs?searchtype=author&query=De%2C+K">Kanjar De</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Q">Qing Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Ao-Xiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Peng Zhang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haibo Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+L">Linyan Jiang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yaqing Li</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+W">Wenhui Meng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhenzhong Chen</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Z">Zhengxue Cheng</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Jiahao Xiao</a> , et al. (7 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.11982v3-abstract-short" style="display: inline;"> Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11982v3-abstract-full').style.display = 'inline'; document.getElementById('2408.11982v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11982v3-abstract-full" style="display: none;"> Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11982v3-abstract-full').style.display = 'none'; document.getElementById('2408.11982v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02208">arXiv:2408.02208</a> <span> [<a href="https://arxiv.org/pdf/2408.02208">pdf</a>, <a href="https://arxiv.org/format/2408.02208">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> <div 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/10.1016/j.trc.2024.104804">10.1016/j.trc.2024.104804 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multi-level Traffic-Responsive Tilt Camera Surveillance through Predictive Correlated Online Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+T">Tao Li</a>, <a href="/search/cs?searchtype=author&query=Bian%2C+Z">Zilin Bian</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+F">Fan Zuo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ya-Ting Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenning Li</a>, <a href="/search/cs?searchtype=author&query=Ozbay%2C+K">Kaan Ozbay</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02208v1-abstract-short" style="display: inline;"> In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitorin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02208v1-abstract-full').style.display = 'inline'; document.getElementById('2408.02208v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02208v1-abstract-full" style="display: none;"> In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitoring and management of traffic in urban networks. By leveraging widely deployed pan-tilt-cameras (PTCs), TTC-X overcomes the limitations of a fixed field of view in traditional surveillance systems by providing mobilized and 360-degree coverage. The innovation of TTC-X lies in the integration of advanced machine learning modules, including a detector-predictor-controller structure, with a novel Predictive Correlated Online Learning (PiCOL) methodology and the Spatial-Temporal Graph Predictor (STGP) for real-time traffic estimation and PTC control. The TTC-X is tested and evaluated under three experimental scenarios (e.g., maximum traffic flow capture, dynamic route planning, traffic state estimation) based on a simulation environment calibrated using real-world traffic data in Brooklyn, New York. The experimental results showed that TTC-X captured over 60\% total number of vehicles at the network level, dynamically adjusted its route recommendation in reaction to unexpected full-lane closure events, and reconstructed link-level traffic states with best MAE less than 1.25 vehicle/hour. Demonstrating scalability, cost-efficiency, and adaptability, TTC-X emerges as a powerful solution for urban traffic management in both cyber-physical and real-world environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02208v1-abstract-full').style.display = 'none'; document.getElementById('2408.02208v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to Transportation Research Part C special issue: Modelling, Learning, and Control of Conventional, Cooperative and Automated Motorway and Urban Traffic Systems</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02095">arXiv:2408.02095</a> <span> [<a href="https://arxiv.org/pdf/2408.02095">pdf</a>, <a href="https://arxiv.org/format/2408.02095">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Secure Semantic Communications: From Perspective of Physical Layer Security </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yongkang Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Zheng Shi</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Han Hu</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yaru Fu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hong Wang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02095v1-abstract-short" style="display: inline;"> Semantic communications have been envisioned as a potential technique that goes beyond Shannon paradigm. Unlike modern communications that provide bit-level security, the eaves-dropping of semantic communications poses a significant risk of potentially exposing intention of legitimate user. To address this challenge, a novel deep neural network (DNN) enabled secure semantic communication (DeepSSC)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02095v1-abstract-full').style.display = 'inline'; document.getElementById('2408.02095v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02095v1-abstract-full" style="display: none;"> Semantic communications have been envisioned as a potential technique that goes beyond Shannon paradigm. Unlike modern communications that provide bit-level security, the eaves-dropping of semantic communications poses a significant risk of potentially exposing intention of legitimate user. To address this challenge, a novel deep neural network (DNN) enabled secure semantic communication (DeepSSC) system is developed by capitalizing on physical layer security. To balance the tradeoff between security and reliability, a two-phase training method for DNNs is devised. Particularly, Phase I aims at semantic recovery of legitimate user, while Phase II attempts to minimize the leakage of semantic information to eavesdroppers. The loss functions of DeepSSC in Phases I and II are respectively designed according to Shannon capacity and secure channel capacity, which are approximated with variational inference. Moreover, we define the metric of secure bilingual evaluation understudy (S-BLEU) to assess the security of semantic communications. Finally, simulation results demonstrate that DeepSSC achieves a significant boost to semantic security particularly in high signal-to-noise ratio regime, despite a minor degradation of reliability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02095v1-abstract-full').style.display = 'none'; document.getElementById('2408.02095v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.17051">arXiv:2407.17051</a> <span> [<a href="https://arxiv.org/pdf/2407.17051">pdf</a>, <a href="https://arxiv.org/ps/2407.17051">ps</a>, <a href="https://arxiv.org/format/2407.17051">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Discrete Mathematics">cs.DM</span> </div> </div> <p class="title is-5 mathjax"> Number of Subgraphs and Their Converses in Tournaments and New Digraph Polynomials </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ai%2C+J">Jiangdong Ai</a>, <a href="/search/cs?searchtype=author&query=Gutin%2C+G">Gregory Gutin</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hui Lei</a>, <a href="/search/cs?searchtype=author&query=Yeo%2C+A">Anders Yeo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yacong Zhou</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="2407.17051v1-abstract-short" style="display: inline;"> An oriented graph $D$ is converse invariant if, for any tournament $T$, the number of copies of $D$ in $T$ is equal to that of its converse $-D$. El Sahili and Ghazo Hanna [J. Graph Theory 102 (2023), 684-701] showed that any oriented graph $D$ with maximum degree at most 2 is converse invariant. They proposed a question: Can we characterize all converse invariant oriented graphs? In this paper,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.17051v1-abstract-full').style.display = 'inline'; document.getElementById('2407.17051v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.17051v1-abstract-full" style="display: none;"> An oriented graph $D$ is converse invariant if, for any tournament $T$, the number of copies of $D$ in $T$ is equal to that of its converse $-D$. El Sahili and Ghazo Hanna [J. Graph Theory 102 (2023), 684-701] showed that any oriented graph $D$ with maximum degree at most 2 is converse invariant. They proposed a question: Can we characterize all converse invariant oriented graphs? In this paper, we introduce a digraph polynomial and employ it to give a necessary condition for an oriented graph to be converse invariant. This polynomial serves as a cornerstone in proving all the results presented in this paper. In particular, we characterize all orientations of trees with diameter at most 3 that are converse invariant. We also show that all orientations of regular graphs are not converse invariant if $D$ and $-D$ have different degree sequences. In addition, in contrast to the findings of El Sahili and Ghazo Hanna, we prove that every connected graph $G$ with maximum degree at least $3$, admits an orientation $D$ of $G$ such that $D$ is not converse invariant. We pose one conjecture. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.17051v1-abstract-full').style.display = 'none'; document.getElementById('2407.17051v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15025">arXiv:2407.15025</a> <span> [<a href="https://arxiv.org/pdf/2407.15025">pdf</a>, <a href="https://arxiv.org/format/2407.15025">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</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"> Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics for Urban Transportation Management </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+T">Tao Li</a>, <a href="/search/cs?searchtype=author&query=Bian%2C+Z">Zilin Bian</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+F">Fan Zuo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ya-Ting Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenning Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhibin Chen</a>, <a href="/search/cs?searchtype=author&query=Ozbay%2C+K">Kaan Ozbay</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="2407.15025v1-abstract-short" style="display: inline;"> Traditional mobility management strategies emphasize macro-level mobility oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics (DT-DIMA) system. The DT-DIMA system integrates real-time traffic information from pan-tilt-cameras (PTCs), synchron… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15025v1-abstract-full').style.display = 'inline'; document.getElementById('2407.15025v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15025v1-abstract-full" style="display: none;"> Traditional mobility management strategies emphasize macro-level mobility oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics (DT-DIMA) system. The DT-DIMA system integrates real-time traffic information from pan-tilt-cameras (PTCs), synchronizes this data into a digital twin to accurately replicate the physical world, and predicts network-wide mobility and safety risks in real time. The system's innovation lies in its integration of spatial-temporal modeling, simulation, and online control modules. Tested and evaluated under normal traffic conditions and incidental situations (e.g., unexpected accidents, pre-planned work zones) in a simulated testbed in Brooklyn, New York, DT-DIMA demonstrated mean absolute percentage errors (MAPEs) ranging from 8.40% to 15.11% in estimating network-level traffic volume and MAPEs from 0.85% to 12.97% in network-level safety risk prediction. In addition, the highly accurate safety risk prediction enables PTCs to preemptively monitor road segments with high driving risks before incidents take place. Such proactive PTC surveillance creates around a 5-minute lead time in capturing traffic incidents. The DT-DIMA system enables transportation managers to understand mobility not only in terms of traffic patterns but also driver-experienced safety risks, allowing for proactive resource allocation in response to various traffic situations. To the authors' best knowledge, DT-DIMA is the first urban mobility management system that considers both mobility and safety risks based on digital twin architecture. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15025v1-abstract-full').style.display = 'none'; document.getElementById('2407.15025v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.10279">arXiv:2407.10279</a> <span> [<a href="https://arxiv.org/pdf/2407.10279">pdf</a>, <a href="https://arxiv.org/format/2407.10279">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+C">Chang Lei</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huan Lei</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="2407.10279v2-abstract-short" style="display: inline;"> Artificial intelligence for card games has long been a popular topic in AI research. In recent years, complex card games like Mahjong and Texas Hold'em have been solved, with corresponding AI programs reaching the level of human experts. However, the game of Doudizhu presents significant challenges due to its vast state/action space and unique characteristics involving reasoning about competition… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.10279v2-abstract-full').style.display = 'inline'; document.getElementById('2407.10279v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.10279v2-abstract-full" style="display: none;"> Artificial intelligence for card games has long been a popular topic in AI research. In recent years, complex card games like Mahjong and Texas Hold'em have been solved, with corresponding AI programs reaching the level of human experts. However, the game of Doudizhu presents significant challenges due to its vast state/action space and unique characteristics involving reasoning about competition and cooperation, making the game extremely difficult to solve.The RL model Douzero, trained using the Deep Monte Carlo algorithm framework, has shown excellent performance in Doudizhu. However, there are differences between its simplified game environment and the actual Doudizhu environment, and its performance is still a considerable distance from that of human experts. This paper modifies the Deep Monte Carlo algorithm framework by using reinforcement learning to obtain a neural network that simultaneously estimates win rates and expectations. The action space is pruned using expectations, and strategies are generated based on win rates. The modified algorithm enables the AI to perform the full range of tasks in the Doudizhu game, including bidding and cardplay. The model was trained in a actual Doudizhu environment and achieved state-of-the-art performance among publicly available models. We hope that this new framework will provide valuable insights for AI development in other bidding-based games. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.10279v2-abstract-full').style.display = 'none'; document.getElementById('2407.10279v2-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">v1</span> submitted 14 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.10147">arXiv:2407.10147</a> <span> [<a href="https://arxiv.org/pdf/2407.10147">pdf</a>, <a href="https://arxiv.org/ps/2407.10147">ps</a>, <a href="https://arxiv.org/format/2407.10147">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Near-Field User Localization and Channel Estimation for XL-MIMO Systems: Fundamentals, Recent Advances, and Outlooks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hao Lei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiayi Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhe Wang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+H">Huahua Xiao</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+B">Bo Ai</a>, <a href="/search/cs?searchtype=author&query=Bj%C3%B6rnson%2C+E">Emil Bj枚rnson</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="2407.10147v1-abstract-short" style="display: inline;"> Extremely large-scale multiple-input multipleoutput (XL-MIMO) is believed to be a cornerstone of sixth-generation (6G) wireless networks. XL-MIMO uses more antennas to both achieve unprecedented spatial degrees of freedom (DoFs) and exploit new electromagnetic (EM) phenomena occurring in the radiative near-field. The near-field effects provide the XL-MIMO array with depth perception, enabling prec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.10147v1-abstract-full').style.display = 'inline'; document.getElementById('2407.10147v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.10147v1-abstract-full" style="display: none;"> Extremely large-scale multiple-input multipleoutput (XL-MIMO) is believed to be a cornerstone of sixth-generation (6G) wireless networks. XL-MIMO uses more antennas to both achieve unprecedented spatial degrees of freedom (DoFs) and exploit new electromagnetic (EM) phenomena occurring in the radiative near-field. The near-field effects provide the XL-MIMO array with depth perception, enabling precise localization and spatially multiplexing jointly in the angle and distance domains. This article delineates the distinctions between near-field and far-field propagation, highlighting the unique EM characteristics introduced by having large antenna arrays. It thoroughly examines the challenges these new near-field characteristics pose for user localization and channel estimation and provides a comprehensive review of new algorithms developed to address them. The article concludes by identifying critical future research directions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.10147v1-abstract-full').style.display = 'none'; document.getElementById('2407.10147v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 4 figures, 2tables, submitted to IEEE WCM</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07314">arXiv:2407.07314</a> <span> [<a href="https://arxiv.org/pdf/2407.07314">pdf</a>, <a href="https://arxiv.org/ps/2407.07314">ps</a>, <a href="https://arxiv.org/format/2407.07314">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> </div> </div> <p class="title is-5 mathjax"> Proactive Eavesdropping in Relay Systems via Trajectory and Power Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dan%2C+Q">Qian Dan</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+W">Weijia Lei</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng 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="2407.07314v1-abstract-short" style="display: inline;"> Wireless relays can effectively extend the transmission range of information. However, if relay technology is utilized unlawfully, it can amplify potential harm. Effectively surveilling illegitimate relay links poses a challenging problem. Unmanned aerial vehicles (UAVs) can proactively surveil wireless relay systems due to their flexible mobility. This work focuses on maximizing the eavesdropping… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07314v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07314v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07314v1-abstract-full" style="display: none;"> Wireless relays can effectively extend the transmission range of information. However, if relay technology is utilized unlawfully, it can amplify potential harm. Effectively surveilling illegitimate relay links poses a challenging problem. Unmanned aerial vehicles (UAVs) can proactively surveil wireless relay systems due to their flexible mobility. This work focuses on maximizing the eavesdropping rate (ER) of UAVs by jointly optimizing the trajectory and jamming power. To address this challenge, we propose a new iterative algorithm based on block coordinate descent and successive convex approximation technologies. Simulation results demonstrate that the proposed algorithm significantly enhances the ER through trajectory and jamming power optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07314v1-abstract-full').style.display = 'none'; document.getElementById('2407.07314v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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, 8 figures, submitted to IEEE Journal for 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/2407.06521">arXiv:2407.06521</a> <span> [<a href="https://arxiv.org/pdf/2407.06521">pdf</a>, <a href="https://arxiv.org/ps/2407.06521">ps</a>, <a href="https://arxiv.org/format/2407.06521">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Beamforming Design for Joint Target Sensing and Proactive Eavesdropping </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dan%2C+Q">Qian Dan</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</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="2407.06521v1-abstract-short" style="display: inline;"> This work studies the beamforming design in the joint target sensing and proactive eavesdropping (JTSAPE) system. The JTSAPE base station (BS) receives the information transmitted by the illegal transmitter and transmits the waveform for target sensing. The shared waveform also serves as artificial noise to interfere with the illegal receiver, thereby achieving proactive eavesdropping. We firstly… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06521v1-abstract-full').style.display = 'inline'; document.getElementById('2407.06521v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.06521v1-abstract-full" style="display: none;"> This work studies the beamforming design in the joint target sensing and proactive eavesdropping (JTSAPE) system. The JTSAPE base station (BS) receives the information transmitted by the illegal transmitter and transmits the waveform for target sensing. The shared waveform also serves as artificial noise to interfere with the illegal receiver, thereby achieving proactive eavesdropping. We firstly optimize the transmitting beam of the BS to maximize the eavesdropping signal-to-interference-plus-noise ratio or minimize the target estimation parameter Cram{茅}r-Rao bound, respectively. Then, the joint optimization of proactive eavesdropping and target sensing is investigated, and the normalized weighted optimization problem is formulated. To address the complexity of the original problem, the formulated problem is decomposed into two subproblems: proactive eavesdropping and target sensing, which are solved by the semi-definite relaxation technique. Furthermore, the scenario in which the quality of the eavesdropping channel is stronger than that of the illegal channel is considered. We utilize the sequential rank-one constraint relaxation method and iteration technique to obtain the high-quality suboptimal solution of the beam transmit covariance matrix. Numerical simulation shows the effectiveness of our proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06521v1-abstract-full').style.display = 'none'; document.getElementById('2407.06521v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, 6 figures, submitted to IEEE Journal for 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/2406.10744">arXiv:2406.10744</a> <span> [<a href="https://arxiv.org/pdf/2406.10744">pdf</a>, <a href="https://arxiv.org/format/2406.10744">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"> Technique Report of CVPR 2024 PBDL Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Ying Fu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yu Li</a>, <a href="/search/cs?searchtype=author&query=You%2C+S">Shaodi You</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+B">Boxin Shi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Linwei Chen</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yunhao Zou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zichun Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yichen Li</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yuze Han</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yingkai Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jianan Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qinglin Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+W">Wei Yu</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+X">Xiaoqian Lv</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jianing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shengping Zhang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+X">Xiangyang Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuanpei Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuhan Zhang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+W">Weihang Peng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Liwen Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhe Xu</a>, <a href="/search/cs?searchtype=author&query=Gou%2C+D">Dingyong Gou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Cong Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Senyan Xu</a> , et al. (75 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="2406.10744v3-abstract-short" style="display: inline;"> The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10744v3-abstract-full').style.display = 'inline'; document.getElementById('2406.10744v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10744v3-abstract-full" style="display: none;"> The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10744v3-abstract-full').style.display = 'none'; document.getElementById('2406.10744v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2024 PBDL Challenges: https://pbdl-ws.github.io/pbdl2024/challenge/index.html</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.06842">arXiv:2406.06842</a> <span> [<a href="https://arxiv.org/pdf/2406.06842">pdf</a>, <a href="https://arxiv.org/ps/2406.06842">ps</a>, <a href="https://arxiv.org/format/2406.06842">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Aerial Relay to Achieve Covertness and Security </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jiacheng Jiang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.06842v1-abstract-short" style="display: inline;"> In this work, a delay-tolerant unmanned aerial vehicle (UAV) relayed covert and secure communication framework is investigated. In this framework, a legitimate UAV serves as an aerial relay to realize communication when the direct link between the terrestrial transmitter and receiver is blocked and also acts as a friendly jammer to suppress the malicious nodes presented on the ground. Subsequently… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06842v1-abstract-full').style.display = 'inline'; document.getElementById('2406.06842v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.06842v1-abstract-full" style="display: none;"> In this work, a delay-tolerant unmanned aerial vehicle (UAV) relayed covert and secure communication framework is investigated. In this framework, a legitimate UAV serves as an aerial relay to realize communication when the direct link between the terrestrial transmitter and receiver is blocked and also acts as a friendly jammer to suppress the malicious nodes presented on the ground. Subsequently, considering the uncertainty of malicious nodes' positions, a robust fractional programming optimization problem is built to maximize energy efficiency by jointly optimizing the trajectory of the UAV, the transmit power of the transmitter, and the time-switching factor. For the extremely complicated covert constraint, Pinsker's inequality, Jensen's inequality, and the bisection search method are employed to construct a tractable shrunken one. After this, an alternate optimization-based algorithm is proposed to solve the fractional programming optimization problem. To achieve low complexity, we design the primal-dual search-based algorithm and the successive convex approximation-based algorithm, respectively, for each sub-problem. Numerical results show the effectiveness of our proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06842v1-abstract-full').style.display = 'none'; document.getElementById('2406.06842v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 6 figures, submitted to IEEE Journal for 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/2406.05936">arXiv:2406.05936</a> <span> [<a href="https://arxiv.org/pdf/2406.05936">pdf</a>, <a href="https://arxiv.org/ps/2406.05936">ps</a>, <a href="https://arxiv.org/format/2406.05936">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> </div> </div> <p class="title is-5 mathjax"> Multi-UAV Trajectory Design for Fair and Secure Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+D">Dongyang Meng</a>, <a href="/search/cs?searchtype=author&query=Ran%2C+H">Haoxiang Ran</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.05936v1-abstract-short" style="display: inline;"> Unmanned aerial vehicles (UAVs) play an essential role in future wireless communication networks due to their high mobility, low cost, and on-demand deployment. In air-to-ground links, UAVs are widely used to enhance the performance of wireless communication systems due to the presence of high-probability line-of-sight (LoS) links. However, the high probability of LoS links also increases the risk… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05936v1-abstract-full').style.display = 'inline'; document.getElementById('2406.05936v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05936v1-abstract-full" style="display: none;"> Unmanned aerial vehicles (UAVs) play an essential role in future wireless communication networks due to their high mobility, low cost, and on-demand deployment. In air-to-ground links, UAVs are widely used to enhance the performance of wireless communication systems due to the presence of high-probability line-of-sight (LoS) links. However, the high probability of LoS links also increases the risk of being eavesdropped, posing a significant challenge to the security of wireless communications. In this work, the secure communication problem in a multi-UAV-assisted communication system is investigated in a moving airborne eavesdropping scenario. To improve the secrecy performance of the considered communication system, aerial eavesdropping capability is suppressed by sending jamming signals from a friendly UAV. An optimization problem under flight conditions, fairness, and limited energy consumption constraints of multiple UAVs is formulated to maximize the fair sum secrecy throughput. Given the complexity and non-convex nature of the problem, we propose a two-step-based optimization approach. The first step employs the $K$-means algorithm to cluster users and associate them with multiple communication UAVs. Then, a multi-agent deep deterministic policy gradient-based algorithm is introduced to solve this optimization problem. The effectiveness of this proposed algorithm is not only theoretically but also rigorously verified by simulation results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05936v1-abstract-full').style.display = 'none'; document.getElementById('2406.05936v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 10 figures, submitted to IEEE Journal for 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/2406.03839">arXiv:2406.03839</a> <span> [<a href="https://arxiv.org/pdf/2406.03839">pdf</a>, <a href="https://arxiv.org/format/2406.03839">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"> PCART: Automated Repair of Python API Parameter Compatibility Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shuai Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+G">Guanping Xiao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huashan Lei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yepang Liu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zheng Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.03839v2-abstract-short" style="display: inline;"> In modern software development, Python third-party libraries have become crucial, particularly due to their widespread use in fields such as deep learning and scientific computing. However, the parameters of APIs in third-party libraries often change during evolution, causing compatibility issues for client applications that depend on specific versions. Due to Python's flexible parameter-passing m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03839v2-abstract-full').style.display = 'inline'; document.getElementById('2406.03839v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03839v2-abstract-full" style="display: none;"> In modern software development, Python third-party libraries have become crucial, particularly due to their widespread use in fields such as deep learning and scientific computing. However, the parameters of APIs in third-party libraries often change during evolution, causing compatibility issues for client applications that depend on specific versions. Due to Python's flexible parameter-passing mechanism, different methods of parameter passing can result in different API compatibility. Currently, no tool is capable of automatically detecting and repairing Python API parameter compatibility issues. To fill this gap, we propose PCART, the first to implement a fully automated process from API extraction, code instrumentation, and API mapping establishment, to compatibility assessment, and finally to repair and validation, for solving various types of Python API parameter compatibility issues, i.e., parameter addition, removal, renaming, reordering of parameters, as well as the conversion of positional parameters to keyword parameters. We construct a large-scale benchmark PCBENCH, including 47,478 test cases mutated from 844 parameter-changed APIs of 33 popular Python libraries, to evaluate PCART. The evaluation results show that PCART is effective yet efficient, significantly outperforming existing tools (MLCatchUp and Relancer) and the large language model ChatGPT-4, achieving an F-measure of 96.49% in detecting API parameter compatibility issues and a repair accuracy of 91.36%. The evaluation on 14 real-world Python projects from GitHub further demonstrates that PCART has good practicality. We believe PCART can help programmers reduce the time spent on maintaining Python API updates and facilitate automated Python API compatibility issue repair. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03839v2-abstract-full').style.display = 'none'; document.getElementById('2406.03839v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Software Engineering</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.01313">arXiv:2406.01313</a> <span> [<a href="https://arxiv.org/pdf/2406.01313">pdf</a>, <a href="https://arxiv.org/ps/2406.01313">ps</a>, <a href="https://arxiv.org/format/2406.01313">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> 3D Trajectory Design for Energy-constrained Aerial CRNs Under Probabilistic LoS Channel </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiaqiu Wu</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng 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="2406.01313v1-abstract-short" style="display: inline;"> Unmanned aerial vehicles (UAVs) have been attracting significant attention because there is a high probability of line-of-sight links being obtained between them and terrestrial nodes in high-rise urban areas. In this work, we investigate cognitive radio networks (CRNs) by jointly designing three-dimensional (3D) trajectory, the transmit power of the UAV, and user scheduling. Considering the UAV's… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01313v1-abstract-full').style.display = 'inline'; document.getElementById('2406.01313v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.01313v1-abstract-full" style="display: none;"> Unmanned aerial vehicles (UAVs) have been attracting significant attention because there is a high probability of line-of-sight links being obtained between them and terrestrial nodes in high-rise urban areas. In this work, we investigate cognitive radio networks (CRNs) by jointly designing three-dimensional (3D) trajectory, the transmit power of the UAV, and user scheduling. Considering the UAV's onboard energy consumption, an optimization problem is formulated in which the average achievable rate of the considered system is maximized by jointly optimizing the UAV's 3D trajectory, transmission power, and user scheduling. Due to the non-convex optimization problem, a lower bound on the average achievable rate is utilized to reduce the complexity of the solution. Subsequently, the original optimization problem is decoupled into four subproblems by using block coordinate descent, and each subproblem is transformed into manageable convex optimization problems by introducing slack variables and successive convex approximation. Numerical results validate the effectiveness of our proposed algorithm and demonstrate that the 3D trajectories of UAVs can enhance the average achievable rate of aerial CRNs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01313v1-abstract-full').style.display = 'none'; document.getElementById('2406.01313v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 6 figures,submitted to the IEEE journal for 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/2404.04492">arXiv:2404.04492</a> <span> [<a href="https://arxiv.org/pdf/2404.04492">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Automated Lane Change Behavior Prediction and Environmental Perception Based on SLAM Technology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Han Lei</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Baoming Wang</a>, <a href="/search/cs?searchtype=author&query=Shui%2C+Z">Zuwei Shui</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+P">Peiyuan Yang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+P">Penghao Liang</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="2404.04492v1-abstract-short" style="display: inline;"> In addition to environmental perception sensors such as cameras, radars, etc. in the automatic driving system, the external environment of the vehicle is perceived, in fact, there is also a perception sensor that has been silently dedicated in the system, that is, the positioning module. This paper explores the application of SLAM (Simultaneous Localization and Mapping) technology in the context o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.04492v1-abstract-full').style.display = 'inline'; document.getElementById('2404.04492v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.04492v1-abstract-full" style="display: none;"> In addition to environmental perception sensors such as cameras, radars, etc. in the automatic driving system, the external environment of the vehicle is perceived, in fact, there is also a perception sensor that has been silently dedicated in the system, that is, the positioning module. This paper explores the application of SLAM (Simultaneous Localization and Mapping) technology in the context of automatic lane change behavior prediction and environment perception for autonomous vehicles. It discusses the limitations of traditional positioning methods, introduces SLAM technology, and compares LIDAR SLAM with visual SLAM. Real-world examples from companies like Tesla, Waymo, and Mobileye showcase the integration of AI-driven technologies, sensor fusion, and SLAM in autonomous driving systems. The paper then delves into the specifics of SLAM algorithms, sensor technologies, and the importance of automatic lane changes in driving safety and efficiency. It highlights Tesla's recent update to its Autopilot system, which incorporates automatic lane change functionality using SLAM technology. The paper concludes by emphasizing the crucial role of SLAM in enabling accurate environment perception, positioning, and decision-making for autonomous vehicles, ultimately enhancing safety and driving experience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.04492v1-abstract-full').style.display = 'none'; document.getElementById('2404.04492v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.03676">arXiv:2403.03676</a> <span> [<a href="https://arxiv.org/pdf/2403.03676">pdf</a>, <a href="https://arxiv.org/format/2403.03676">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"> Simplified PCNet with Robustness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+B">Bingheng Li</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+X">Xuanting Xie</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haoxiang Lei</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+R">Ruiyi Fang</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+Z">Zhao Kang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.03676v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs. However, they cannot generalize well to real-world graphs with different levels of homophily. In response, the Possion-Charlier Network (PCNet) \cite{li2024pc}, the previous work, allows graph representation to be learned from heterophily to homoph… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03676v1-abstract-full').style.display = 'inline'; document.getElementById('2403.03676v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.03676v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs. However, they cannot generalize well to real-world graphs with different levels of homophily. In response, the Possion-Charlier Network (PCNet) \cite{li2024pc}, the previous work, allows graph representation to be learned from heterophily to homophily. Although PCNet alleviates the heterophily issue, there remain some challenges in further improving the efficacy and efficiency. In this paper, we simplify PCNet and enhance its robustness. We first extend the filter order to continuous values and reduce its parameters. Two variants with adaptive neighborhood sizes are implemented. Theoretical analysis shows our model's robustness to graph structure perturbations or adversarial attacks. We validate our approach through semi-supervised learning tasks on various datasets representing both homophilic and heterophilic graphs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03676v1-abstract-full').style.display = 'none'; document.getElementById('2403.03676v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 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/2402.18129">arXiv:2402.18129</a> <span> [<a href="https://arxiv.org/pdf/2402.18129">pdf</a>, <a href="https://arxiv.org/format/2402.18129">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="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haoyu Lei</a>, <a href="/search/cs?searchtype=author&query=Gohari%2C+A">Amin Gohari</a>, <a href="/search/cs?searchtype=author&query=Farnia%2C+F">Farzan Farnia</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.18129v2-abstract-short" style="display: inline;"> Fair supervised learning algorithms assigning labels with little dependence on a sensitive attribute have attracted great attention in the machine learning community. While the demographic parity (DP) notion has been frequently used to measure a model's fairness in training fair classifiers, several studies in the literature suggest potential impacts of enforcing DP in fair learning algorithms. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18129v2-abstract-full').style.display = 'inline'; document.getElementById('2402.18129v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.18129v2-abstract-full" style="display: none;"> Fair supervised learning algorithms assigning labels with little dependence on a sensitive attribute have attracted great attention in the machine learning community. While the demographic parity (DP) notion has been frequently used to measure a model's fairness in training fair classifiers, several studies in the literature suggest potential impacts of enforcing DP in fair learning algorithms. In this work, we analytically study the effect of standard DP-based regularization methods on the conditional distribution of the predicted label given the sensitive attribute. Our analysis shows that an imbalanced training dataset with a non-uniform distribution of the sensitive attribute could lead to a classification rule biased toward the sensitive attribute outcome holding the majority of training data. To control such inductive biases in DP-based fair learning, we propose a sensitive attribute-based distributionally robust optimization (SA-DRO) method improving robustness against the marginal distribution of the sensitive attribute. Finally, we present several numerical results on the application of DP-based learning methods to standard centralized and distributed learning problems. The empirical findings support our theoretical results on the inductive biases in DP-based fair learning algorithms and the debiasing effects of the proposed SA-DRO method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18129v2-abstract-full').style.display = 'none'; document.getElementById('2402.18129v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.16131">arXiv:2402.16131</a> <span> [<a href="https://arxiv.org/pdf/2402.16131">pdf</a>, <a href="https://arxiv.org/format/2402.16131">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="Methodology">stat.ME</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"> A VAE-based Framework for Learning Multi-Level Neural Granger-Causal Connectivity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+J">Jiahe Lin</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huitian Lei</a>, <a href="/search/cs?searchtype=author&query=Michailidis%2C+G">George Michailidis</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.16131v1-abstract-short" style="display: inline;"> Granger causality has been widely used in various application domains to capture lead-lag relationships amongst the components of complex dynamical systems, and the focus in extant literature has been on a single dynamical system. In certain applications in macroeconomics and neuroscience, one has access to data from a collection of related such systems, wherein the modeling task of interest is to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.16131v1-abstract-full').style.display = 'inline'; document.getElementById('2402.16131v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.16131v1-abstract-full" style="display: none;"> Granger causality has been widely used in various application domains to capture lead-lag relationships amongst the components of complex dynamical systems, and the focus in extant literature has been on a single dynamical system. In certain applications in macroeconomics and neuroscience, one has access to data from a collection of related such systems, wherein the modeling task of interest is to extract the shared common structure that is embedded across them, as well as to identify the idiosyncrasies within individual ones. This paper introduces a Variational Autoencoder (VAE) based framework that jointly learns Granger-causal relationships amongst components in a collection of related-yet-heterogeneous dynamical systems, and handles the aforementioned task in a principled way. The performance of the proposed framework is evaluated on several synthetic data settings and benchmarked against existing approaches designed for individual system learning. The method is further illustrated on a real dataset involving time series data from a neurophysiological experiment and produces interpretable results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.16131v1-abstract-full').style.display = 'none'; document.getElementById('2402.16131v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by Transactions on Machine Learning Research</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.02344">arXiv:2402.02344</a> <span> [<a href="https://arxiv.org/pdf/2402.02344">pdf</a>, <a href="https://arxiv.org/ps/2402.02344">ps</a>, <a href="https://arxiv.org/format/2402.02344">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> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/JIOT.2024.3370161">10.1109/JIOT.2024.3370161 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> On Secure mmWave RSMA Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Sha Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinhu Chen</a>, <a href="/search/cs?searchtype=author&query=Ansari%2C+I+S">Imran Shafique Ansari</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yun Li</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.02344v2-abstract-short" style="display: inline;"> This work considers a multiple-input-single-output mmWave RSMA system wherein a base station serves two users in the presence of a passive eavesdropper. Different eavesdropping scenarios are considered corresponding to the overlapped resolvable paths between the main and the wiretap channels under the considered transmission schemes. The analytical expressions for the secrecy outage probability ar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.02344v2-abstract-full').style.display = 'inline'; document.getElementById('2402.02344v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.02344v2-abstract-full" style="display: none;"> This work considers a multiple-input-single-output mmWave RSMA system wherein a base station serves two users in the presence of a passive eavesdropper. Different eavesdropping scenarios are considered corresponding to the overlapped resolvable paths between the main and the wiretap channels under the considered transmission schemes. The analytical expressions for the secrecy outage probability are derived respectively through the Gaussian Chebyshev quadrature method. Monte Carlo simulation results are presented to validate the correctness of the derived analytical expressions and demonstrate the effects of system parameters on the SOP of the considered mmWave RSMA systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.02344v2-abstract-full').style.display = 'none'; document.getElementById('2402.02344v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages,8 figures, accepted by IEEE Internet of Things 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/2312.04328">arXiv:2312.04328</a> <span> [<a href="https://arxiv.org/pdf/2312.04328">pdf</a>, <a href="https://arxiv.org/format/2312.04328">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> A Multi-scale Information Integration Framework for Infrared and Visible Image Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jie Li</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hanxiao Lei</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xinbo Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.04328v2-abstract-short" style="display: inline;"> Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality images from the same scene. Existing methods mostly adopt a simple weight in the loss function to decide the information retention of each modality rather than… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.04328v2-abstract-full').style.display = 'inline'; document.getElementById('2312.04328v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.04328v2-abstract-full" style="display: none;"> Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality images from the same scene. Existing methods mostly adopt a simple weight in the loss function to decide the information retention of each modality rather than adaptively measuring complementary information for different image pairs. In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level. In our method, the residual downsample block decomposes source images into three scales first. Then, dual attention fusion block integrates complementary information and generates a spatial and channel attention map at each scale for feature fusion. Finally, the output image is reconstructed by the residual reconstruction block. Loss function consists of image-level, feature-level and patch-level three parts, of which the calculation of the image-level and patch-level two parts are based on the weights generated by the complementary information measurement. Indeed, to constrain the pixel intensity distribution between the output and infrared image, a style loss is added. Our fusion results perform robust and informative across different scenarios. Qualitative and quantitative results on two datasets illustrate that our method is able to preserve both thermal radiation and detailed information from two modalities and achieve comparable results compared with the other state-of-the-art methods. Ablation experiments show the effectiveness of our information integration architecture and adaptively measure complementary information retention in the loss function. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.04328v2-abstract-full').style.display = 'none'; document.getElementById('2312.04328v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.14200">arXiv:2310.14200</a> <span> [<a href="https://arxiv.org/pdf/2310.14200">pdf</a>, <a href="https://arxiv.org/ps/2310.14200">ps</a>, <a href="https://arxiv.org/format/2310.14200">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> </div> </div> <p class="title is-5 mathjax"> Dynamic Resource Management in CDRT Systems through Adaptive NOMA </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Mingxu Yang</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Saeed%2C+N">Nasir Saeed</a>, <a href="/search/cs?searchtype=author&query=She%2C+X">Xusheng She</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jianling Cao</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="2310.14200v1-abstract-short" style="display: inline;"> This paper introduces a novel adaptive transmission scheme to amplify the prowess of coordinated direct and relay transmission (CDRT) systems rooted in non-orthogonal multiple access principles. Leveraging the maximum ratio transmission scheme, we seamlessly meet the prerequisites of CDRT while harnessing the potential of dynamic power allocation and directional antennas to elevate the system's op… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14200v1-abstract-full').style.display = 'inline'; document.getElementById('2310.14200v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.14200v1-abstract-full" style="display: none;"> This paper introduces a novel adaptive transmission scheme to amplify the prowess of coordinated direct and relay transmission (CDRT) systems rooted in non-orthogonal multiple access principles. Leveraging the maximum ratio transmission scheme, we seamlessly meet the prerequisites of CDRT while harnessing the potential of dynamic power allocation and directional antennas to elevate the system's operational efficiency. Through meticulous derivations, we unveil closed-form expressions depicting the exact effective sum throughput. Our simulation results adeptly validate the theoretical analysis and vividly showcase the effectiveness of the proposed scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14200v1-abstract-full').style.display = 'none'; document.getElementById('2310.14200v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 7 figures, submitted to IEEE journal for 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/2310.13932">arXiv:2310.13932</a> <span> [<a href="https://arxiv.org/pdf/2310.13932">pdf</a>, <a href="https://arxiv.org/ps/2310.13932">ps</a>, <a href="https://arxiv.org/format/2310.13932">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Trajectory and Power Design for Aerial Multi-User Covert Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jiacheng Jiang</a>, <a href="/search/cs?searchtype=author&query=Ansari%2C+I+S">Imran Shafique Ansari</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</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="2310.13932v1-abstract-short" style="display: inline;"> Unmanned aerial vehicles (UAVs) can provide wireless access to terrestrial users, regardless of geographical constraints, and will be an important part of future communication systems. In this paper, a multi-user downlink dual-UAVs enabled covert communication system was investigated, in which a UAV transmits secure information to ground users in the presence of multiple wardens as well as a frien… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13932v1-abstract-full').style.display = 'inline'; document.getElementById('2310.13932v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13932v1-abstract-full" style="display: none;"> Unmanned aerial vehicles (UAVs) can provide wireless access to terrestrial users, regardless of geographical constraints, and will be an important part of future communication systems. In this paper, a multi-user downlink dual-UAVs enabled covert communication system was investigated, in which a UAV transmits secure information to ground users in the presence of multiple wardens as well as a friendly jammer UAV transmits artificial jamming signals to fight with the wardens. The scenario of wardens being outfitted with a single antenna is considered, and the detection error probability (DEP) of wardens with finite observations is researched. Then, considering the uncertainty of wardens' location, a robust optimization problem with worst-case covertness constraint is formulated to maximize the average covert rate by jointly optimizing power allocation and trajectory. To cope with the optimization problem, an algorithm based on successive convex approximation methods is proposed. Thereafter, the results are extended to the case where all the wardens are equipped with multiple antennas. After analyzing the DEP in this scenario, a tractable lower bound of the DEP is obtained by utilizing Pinsker's inequality. Subsequently, the non-convex optimization problem was established and efficiently coped by utilizing a similar algorithm as in the single-antenna scenario. Numerical results indicate the effectiveness of our proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13932v1-abstract-full').style.display = 'none'; document.getElementById('2310.13932v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">30 pages, 9 figures, submitted to the IEEE journal for 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/2310.13931">arXiv:2310.13931</a> <span> [<a href="https://arxiv.org/pdf/2310.13931">pdf</a>, <a href="https://arxiv.org/ps/2310.13931">ps</a>, <a href="https://arxiv.org/format/2310.13931">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Trajectory and power design for aerial CRNs with colluding eavesdroppers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jiacheng Jiang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haosi Yang</a>, <a href="/search/cs?searchtype=author&query=Park%2C+K">Ki-Hong Park</a>, <a href="/search/cs?searchtype=author&query=Ansari%2C+I+S">Imran Shafique Ansari</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+G">Gaofeng Pan</a>, <a href="/search/cs?searchtype=author&query=Alouini%2C+M">Mohamed-Slim Alouini</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="2310.13931v1-abstract-short" style="display: inline;"> Unmanned aerial vehicles (UAVs) can provide wireless access services to terrestrial users without geographical limitations and will become an essential part of the future communication system. However, the openness of wireless channels and the mobility of UAVs make the security of UAV-based communication systems particularly challenging. This work investigates the security of aerial cognitive radi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13931v1-abstract-full').style.display = 'inline'; document.getElementById('2310.13931v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13931v1-abstract-full" style="display: none;"> Unmanned aerial vehicles (UAVs) can provide wireless access services to terrestrial users without geographical limitations and will become an essential part of the future communication system. However, the openness of wireless channels and the mobility of UAVs make the security of UAV-based communication systems particularly challenging. This work investigates the security of aerial cognitive radio networks (CRNs) with multiple uncertainties colluding eavesdroppers. A cognitive aerial base station transmits messages to cognitive terrestrial users using the spectrum resource of the primary users. All secondary terrestrial users and illegitimate receivers jointly decode the received message. The average secrecy rate of the aerial CRNs is maximized by jointly optimizing the UAV's trajectory and transmission power. An iterative algorithm based on block coordinate descent and successive convex approximation is proposed to solve the non-convex mixed-variable optimization problem. Numerical results verify the effectiveness of our proposed algorithm and show that our scheme improves the secrecy performance of airborne CRNs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13931v1-abstract-full').style.display = 'none'; document.getElementById('2310.13931v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 7 figures.submitted to the IEEE journal for 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/2310.01646">arXiv:2310.01646</a> <span> [<a href="https://arxiv.org/pdf/2310.01646">pdf</a>, <a href="https://arxiv.org/format/2310.01646">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Strategic Information Attacks on Incentive-Compatible Navigational Recommendations in Intelligent Transportation Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Ya-Ting Yang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan 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="2310.01646v1-abstract-short" style="display: inline;"> Intelligent transportation systems (ITS) have gained significant attention from various communities, driven by rapid advancements in informational technology. Within the realm of ITS, navigational recommendation systems (RS) play a pivotal role, as users often face diverse path (route) options in such complex urban environments. However, RS is not immune to vulnerabilities, especially when confron… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01646v1-abstract-full').style.display = 'inline'; document.getElementById('2310.01646v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.01646v1-abstract-full" style="display: none;"> Intelligent transportation systems (ITS) have gained significant attention from various communities, driven by rapid advancements in informational technology. Within the realm of ITS, navigational recommendation systems (RS) play a pivotal role, as users often face diverse path (route) options in such complex urban environments. However, RS is not immune to vulnerabilities, especially when confronted with potential information-based attacks. This study aims to explore the impacts of these cyber threats on RS, explicitly focusing on local targeted information attacks in which the attacker favors certain groups or businesses. We study human behaviors and propose the coordinated incentive-compatible RS that guides users toward a mixed Nash equilibrium, under which each user has no incentive to deviate from the recommendation. Then, we delve into the vulnerabilities within the recommendation process, focusing on scenarios involving misinformed demands. In such cases, the attacker can fabricate fake users to mislead the RS's recommendations. Using the Stackelberg game approach, the analytical results and the numerical case study reveal that RS is susceptible to informational attacks. This study highlights the need to consider informational attacks for a more resilient and effective navigational recommendation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01646v1-abstract-full').style.display = 'none'; document.getElementById('2310.01646v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 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/2309.02328">arXiv:2309.02328</a> <span> [<a href="https://arxiv.org/pdf/2309.02328">pdf</a>, <a href="https://arxiv.org/format/2309.02328">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="Systems and Control">eess.SY</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"> Neurosymbolic Meta-Reinforcement Lookahead Learning Achieves Safe Self-Driving in Non-Stationary Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan 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="2309.02328v1-abstract-short" style="display: inline;"> In the area of learning-driven artificial intelligence advancement, the integration of machine learning (ML) into self-driving (SD) technology stands as an impressive engineering feat. Yet, in real-world applications outside the confines of controlled laboratory scenarios, the deployment of self-driving technology assumes a life-critical role, necessitating heightened attention from researchers to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02328v1-abstract-full').style.display = 'inline'; document.getElementById('2309.02328v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.02328v1-abstract-full" style="display: none;"> In the area of learning-driven artificial intelligence advancement, the integration of machine learning (ML) into self-driving (SD) technology stands as an impressive engineering feat. Yet, in real-world applications outside the confines of controlled laboratory scenarios, the deployment of self-driving technology assumes a life-critical role, necessitating heightened attention from researchers towards both safety and efficiency. To illustrate, when a self-driving model encounters an unfamiliar environment in real-time execution, the focus must not solely revolve around enhancing its anticipated performance; equal consideration must be given to ensuring its execution or real-time adaptation maintains a requisite level of safety. This study introduces an algorithm for online meta-reinforcement learning, employing lookahead symbolic constraints based on \emph{Neurosymbolic Meta-Reinforcement Lookahead Learning} (NUMERLA). NUMERLA proposes a lookahead updating mechanism that harmonizes the efficiency of online adaptations with the overarching goal of ensuring long-term safety. Experimental results demonstrate NUMERLA confers the self-driving agent with the capacity for real-time adaptability, leading to safe and self-adaptive driving under non-stationary urban human-vehicle interaction scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02328v1-abstract-full').style.display = 'none'; document.getElementById('2309.02328v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.16400">arXiv:2308.16400</a> <span> [<a href="https://arxiv.org/pdf/2308.16400">pdf</a>, <a href="https://arxiv.org/ps/2308.16400">ps</a>, <a href="https://arxiv.org/format/2308.16400">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Channel Estimation for XL-MIMO Systems with Polar-Domain Multi-Scale Residual Dense Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hao Lei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiayi Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+H">Huahua Xiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaodan Zhang</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+B">Bo Ai</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+D+W+K">Derrick Wing Kwan Ng</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="2308.16400v2-abstract-short" style="display: inline;"> Extremely large-scale multiple-input multiple-output (XL-MIMO) is a promising technique to enable versatile applications for future wireless communications.To realize the huge potential performance gain, accurate channel state information is a fundamental technical prerequisite. In conventional massive MIMO, the channel is often modeled by the far-field planar-wavefront with rich sparsity in the a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.16400v2-abstract-full').style.display = 'inline'; document.getElementById('2308.16400v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.16400v2-abstract-full" style="display: none;"> Extremely large-scale multiple-input multiple-output (XL-MIMO) is a promising technique to enable versatile applications for future wireless communications.To realize the huge potential performance gain, accurate channel state information is a fundamental technical prerequisite. In conventional massive MIMO, the channel is often modeled by the far-field planar-wavefront with rich sparsity in the angular domain that facilitates the design of low-complexity channel estimation. However, this sparsity is not conspicuous in XL-MIMO systems due to the non-negligible near-field spherical-wavefront. To address the inherent performance loss of the angular-domain channel estimation schemes, we first propose the polar-domain multiple residual dense network (P-MRDN) for XL-MIMO systems based on the polar-domain sparsity of the near-field channel by improving the existing MRDN scheme. Furthermore, a polar-domain multi-scale residual dense network (P-MSRDN) is designed to improve the channel estimation accuracy. Finally, simulation results reveal the superior performance of the proposed schemes compared with existing benchmark schemes and the minimal influence of the channel sparsity on the proposed schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.16400v2-abstract-full').style.display = 'none'; document.getElementById('2308.16400v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.09708">arXiv:2308.09708</a> <span> [<a href="https://arxiv.org/pdf/2308.09708">pdf</a>, <a href="https://arxiv.org/format/2308.09708">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"> Training with Product Digital Twins for AutoRetail Checkout </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yue Yao</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+X">Xinyu Tian</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Z">Zheng Tang</a>, <a href="/search/cs?searchtype=author&query=Biswas%2C+S">Sujit Biswas</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huan Lei</a>, <a href="/search/cs?searchtype=author&query=Gedeon%2C+T">Tom Gedeon</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+L">Liang Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.09708v1-abstract-short" style="display: inline;"> Automating the checkout process is important in smart retail, where users effortlessly pass products by hand through a camera, triggering automatic product detection, tracking, and counting. In this emerging area, due to the lack of annotated training data, we introduce a dataset comprised of product 3D models, which allows for fast, flexible, and large-scale training data generation through graph… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09708v1-abstract-full').style.display = 'inline'; document.getElementById('2308.09708v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.09708v1-abstract-full" style="display: none;"> Automating the checkout process is important in smart retail, where users effortlessly pass products by hand through a camera, triggering automatic product detection, tracking, and counting. In this emerging area, due to the lack of annotated training data, we introduce a dataset comprised of product 3D models, which allows for fast, flexible, and large-scale training data generation through graphic engine rendering. Within this context, we discern an intriguing facet, because of the user "hands-on" approach, bias in user behavior leads to distinct patterns in the real checkout process. The existence of such patterns would compromise training effectiveness if training data fail to reflect the same. To address this user bias problem, we propose a training data optimization framework, i.e., training with digital twins (DtTrain). Specifically, we leverage the product 3D models and optimize their rendering viewpoint and illumination to generate "digital twins" that visually resemble representative user images. These digital twins, inherit product labels and, when augmented, form the Digital Twin training set (DT set). Because the digital twins individually mimic user bias, the resulting DT training set better reflects the characteristics of the target scenario and allows us to train more effective product detection and tracking models. In our experiment, we show that DT set outperforms training sets created by existing dataset synthesis methods in terms of counting accuracy. Moreover, by combining DT set with pseudo-labeled real checkout data, further improvement is observed. The code is available at https://github.com/yorkeyao/Automated-Retail-Checkout. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09708v1-abstract-full').style.display = 'none'; document.getElementById('2308.09708v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.02140">arXiv:2308.02140</a> <span> [<a href="https://arxiv.org/pdf/2308.02140">pdf</a>, <a href="https://arxiv.org/ps/2308.02140">ps</a>, <a href="https://arxiv.org/format/2308.02140">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Deep Reinforcement Learning Empowered Rate Selection of XP-HARQ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+D">Da Wu</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+J">Jiahui Feng</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Zheng Shi</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guanghua Yang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+S">Shaodan Ma</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="2308.02140v1-abstract-short" style="display: inline;"> The complex transmission mechanism of cross-packet hybrid automatic repeat request (XP-HARQ) hinders its optimal system design. To overcome this difficulty, this letter attempts to use the deep reinforcement learning (DRL) to solve the rate selection problem of XP-HARQ over correlated fading channels. In particular, the long term average throughput (LTAT) is maximized by properly choosing the incr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.02140v1-abstract-full').style.display = 'inline'; document.getElementById('2308.02140v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.02140v1-abstract-full" style="display: none;"> The complex transmission mechanism of cross-packet hybrid automatic repeat request (XP-HARQ) hinders its optimal system design. To overcome this difficulty, this letter attempts to use the deep reinforcement learning (DRL) to solve the rate selection problem of XP-HARQ over correlated fading channels. In particular, the long term average throughput (LTAT) is maximized by properly choosing the incremental information rate for each HARQ round on the basis of the outdated channel state information (CSI) available at the transmitter. The rate selection problem is first converted into a Markov decision process (MDP), which is then solved by capitalizing on the algorithm of deep deterministic policy gradient (DDPG) with prioritized experience replay. The simulation results finally corroborate the superiority of the proposed XP-HARQ scheme over the conventional HARQ with incremental redundancy (HARQ-IR) and the XP-HARQ with only statistical CSI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.02140v1-abstract-full').style.display = 'none'; document.getElementById('2308.02140v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15929">arXiv:2307.15929</a> <span> [<a href="https://arxiv.org/pdf/2307.15929">pdf</a>, <a href="https://arxiv.org/format/2307.15929">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="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Secure HARQ-IR-Aided Terahertz Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yongkang Li</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Z">Ziyang Song</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Zheng Shi</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Q">Qingping Dou</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hongjiang Lei</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+J">Jinming Wen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Junbin 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="2307.15929v1-abstract-short" style="display: inline;"> Terahertz (THz) communication is one of the most promising candidates to accommodate high-speed mobile data services. This paper proposes a secure hybrid automatic repeat request with incremental redundancy (HARQ-IR) aided THz communication scheme, where the transmission secrecy is ensured by confusing the eavesdropper with dummy messages. The connection and secrecy outage probabilities are then d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15929v1-abstract-full').style.display = 'inline'; document.getElementById('2307.15929v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15929v1-abstract-full" style="display: none;"> Terahertz (THz) communication is one of the most promising candidates to accommodate high-speed mobile data services. This paper proposes a secure hybrid automatic repeat request with incremental redundancy (HARQ-IR) aided THz communication scheme, where the transmission secrecy is ensured by confusing the eavesdropper with dummy messages. The connection and secrecy outage probabilities are then derived in closed-form. Besides, the tail behaviour of the connection outage probability in high signal-to-noise ratio (SNR) is examined by carrying out the asymptotic analysis, and the upper bound of the secrecy outage probability is obtained in a simple form by capitalizing on large deviations. With these results, we take a step further to investigate the secrecy long term average throughput (LTAT). By noticing that HARQ-IR not only improves the reliability of the legitimate user, but also increases the probability of being eavesdropped, a robust rate adaption policy is finally proposed to maximize the LTAT while restricting the connection and secrecy outage probabilities within satisfactory requirements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15929v1-abstract-full').style.display = 'none'; document.getElementById('2307.15929v1-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.02830">arXiv:2307.02830</a> <span> [<a href="https://arxiv.org/pdf/2307.02830">pdf</a>, <a href="https://arxiv.org/format/2307.02830">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"> Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xuefeng Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liwen Wang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+G">Guanting Dong</a>, <a href="/search/cs?searchtype=author&query=He%2C+K">Keqing He</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jinzheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Hao Lei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jiachi Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+W">Weiran 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="2307.02830v1-abstract-short" style="display: inline;"> Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain. Existing models either encode slot descriptions and examples or design handcrafted question templates using heuristic rules, suffering from poor generalization capability or robustness. In this paper, we propose a generative zero-shot prompt learning framework for cross-dom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02830v1-abstract-full').style.display = 'inline'; document.getElementById('2307.02830v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.02830v1-abstract-full" style="display: none;"> Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain. Existing models either encode slot descriptions and examples or design handcrafted question templates using heuristic rules, suffering from poor generalization capability or robustness. In this paper, we propose a generative zero-shot prompt learning framework for cross-domain slot filling, both improving generalization and robustness than previous work. Besides, we introduce a novel inverse prompting strategy to distinguish different slot types to avoid the multiple prediction problem, and an efficient prompt-tuning strategy to boost higher performance by only training fewer prompt parameters. Experiments and analysis demonstrate the effectiveness of our proposed framework, especially huge improvements (+13.44% F1) on the unseen slots. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02830v1-abstract-full').style.display = 'none'; document.getElementById('2307.02830v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the Findings of ACL2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.06766">arXiv:2306.06766</a> <span> [<a href="https://arxiv.org/pdf/2306.06766">pdf</a>, <a href="https://arxiv.org/format/2306.06766">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+T">Tao Li</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Haozhe Lei</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hao Guo</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mingsheng Yin</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yaqi Hu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Quanyan Zhu</a>, <a href="/search/cs?searchtype=author&query=Rangan%2C+S">Sundeep Rangan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.06766v3-abstract-short" style="display: inline;"> Millimeter-wave (mmWave) communication is a vital component of future generations of mobile networks, offering not only high data rates but also precise beams, making it ideal for indoor navigation in complex environments. However, the challenges of multipath propagation and noisy signal measurements in indoor spaces complicate the use of mmWave signals for navigation tasks. Traditional physics-ba… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.06766v3-abstract-full').style.display = 'inline'; document.getElementById('2306.06766v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.06766v3-abstract-full" style="display: none;"> Millimeter-wave (mmWave) communication is a vital component of future generations of mobile networks, offering not only high data rates but also precise beams, making it ideal for indoor navigation in complex environments. However, the challenges of multipath propagation and noisy signal measurements in indoor spaces complicate the use of mmWave signals for navigation tasks. Traditional physics-based methods, such as following the angle of arrival (AoA), often fall short in complex scenarios, highlighting the need for more sophisticated approaches. Digital twins, as virtual replicas of physical environments, offer a powerful tool for simulating and optimizing mmWave signal propagation in such settings. By creating detailed, physics-based models of real-world spaces, digital twins enable the training of machine learning algorithms in virtual environments, reducing the costs and limitations of physical testing. Despite their advantages, current machine learning models trained in digital twins often overfit specific virtual environments and require costly retraining when applied to new scenarios. In this paper, we propose a Physics-Informed Reinforcement Learning (PIRL) approach that leverages the physical insights provided by digital twins to shape the reinforcement learning (RL) reward function. By integrating physics-based metrics such as signal strength, AoA, and path reflections into the learning process, PIRL enables efficient learning and improved generalization to new environments without retraining. Our experiments demonstrate that the proposed PIRL, supported by digital twin simulations, outperforms traditional heuristics and standard RL models, achieving zero-shot generalization in unseen environments and offering a cost-effective, scalable solution for wireless indoor navigation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.06766v3-abstract-full').style.display = 'none'; document.getElementById('2306.06766v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Open Journal of the Communications Society</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.14380">arXiv:2305.14380</a> <span> [<a href="https://arxiv.org/pdf/2305.14380">pdf</a>, <a href="https://arxiv.org/format/2305.14380">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Finding the Pillars of Strength for Multi-Head Attention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ni%2C+J">Jinjie Ni</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+R">Rui Mao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zonglin Yang</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Han Lei</a>, <a href="/search/cs?searchtype=author&query=Cambria%2C+E">Erik Cambria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.14380v2-abstract-short" style="display: inline;"> Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming performance. Inspired by the minimum-redunda… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.14380v2-abstract-full').style.display = 'inline'; document.getElementById('2305.14380v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.14380v2-abstract-full" style="display: none;"> Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming performance. Inspired by the minimum-redundancy feature selection, we assume that focusing on the most representative and distinctive features with minimum resources can mitigate the above issues and lead to more effective and efficient MHAs. In particular, we propose Grouped Head Attention, trained with a self-supervised group constraint that group attention heads, where each group focuses on an essential but distinctive feature subset. We additionally propose a Voting-to-Stay procedure to remove redundant heads, thus achieving a transformer with lighter weights. Moreover, our method achieves significant performance gains on three well-established tasks while considerably compressing parameters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.14380v2-abstract-full').style.display = 'none'; document.getElementById('2305.14380v2-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2023)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.0; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.16186">arXiv:2303.16186</a> <span> [<a href="https://arxiv.org/pdf/2303.16186">pdf</a>, <a href="https://arxiv.org/format/2303.16186">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"> Large-scale Training Data Search for Object Re-identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yue Yao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+H">Huan Lei</a>, <a href="/search/cs?searchtype=author&query=Gedeon%2C+T">Tom Gedeon</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+L">Liang Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.16186v1-abstract-short" style="display: inline;"> We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained. We propose a search and pruning (SnP) solution to this training data search problem, tailored to object re-identification (re-ID), an appli… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16186v1-abstract-full').style.display = 'inline'; document.getElementById('2303.16186v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.16186v1-abstract-full" style="display: none;"> We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained. We propose a search and pruning (SnP) solution to this training data search problem, tailored to object re-identification (re-ID), an application aiming to match the same object captured by different cameras. Specifically, the search stage identifies and merges clusters of source identities which exhibit similar distributions with the target domain. The second stage, subject to a budget, then selects identities and their images from the Stage I output, to control the size of the resulting training set for efficient training. The two steps provide us with training sets 80\% smaller than the source pool while achieving a similar or even higher re-ID accuracy. These training sets are also shown to be superior to a few existing search methods such as random sampling and greedy sampling under the same budget on training data size. If we release the budget, training sets resulting from the first stage alone allow even higher re-ID accuracy. We provide interesting discussions on the specificity of our method to the re-ID problem and particularly its role in bridging the re-ID domain gap. The code is available at https://github.com/yorkeyao/SnP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16186v1-abstract-full').style.display = 'none'; document.getElementById('2303.16186v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to CVPR2023</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Lei%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Lei%2C+H&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository