Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 1,758 results for author: <span class="mathjax">Zhao, Z</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=Zhao%2C+Z">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="Zhao, Z"> </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=Zhao%2C+Z&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="Zhao, Z"> <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=Zhao%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14401">arXiv:2411.14401</a> <span> [<a href="https://arxiv.org/pdf/2411.14401">pdf</a>, <a href="https://arxiv.org/format/2411.14401">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiming Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhuokai Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhaorun Chen</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Zenghui Ding</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xianjun Yang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yining Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.14401v1-abstract-short" style="display: inline;"> Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely heavily on fine-tuning to capture nuanced spatial-temporal details, which incurs significant data and computation costs. In contrast, training-free approaches, though… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14401v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14401v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14401v1-abstract-full" style="display: none;"> Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely heavily on fine-tuning to capture nuanced spatial-temporal details, which incurs significant data and computation costs. In contrast, training-free approaches, though efficient, often lack robustness in preserving context-rich features across complex video content. To this end, we propose DYTO, a novel dynamic token merging framework for zero-shot video understanding that adaptively optimizes token efficiency while preserving crucial scene details. DYTO integrates a hierarchical frame selection and a bipartite token merging strategy to dynamically cluster key frames and selectively compress token sequences, striking a balance between computational efficiency with semantic richness. Extensive experiments across multiple benchmarks demonstrate the effectiveness of DYTO, achieving superior performance compared to both fine-tuned and training-free methods and setting a new state-of-the-art for zero-shot video understanding. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14401v1-abstract-full').style.display = 'none'; document.getElementById('2411.14401v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14243">arXiv:2411.14243</a> <span> [<a href="https://arxiv.org/pdf/2411.14243">pdf</a>, <a href="https://arxiv.org/format/2411.14243">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 Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jialin Lu</a>, <a href="/search/cs?searchtype=author&query=Shan%2C+J">Junjie Shan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziqi Zhao</a>, <a href="/search/cs?searchtype=author&query=Chow%2C+K">Ka-Ho Chow</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="2411.14243v1-abstract-short" style="display: inline;"> As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a significant threat by implanting hidden backdoor in a victim model, which adversaries can later exploit to trigger malicious behaviors during inference. However, current backdoor techniques are limited to static scenarios where attackers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14243v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14243v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14243v1-abstract-full" style="display: none;"> As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a significant threat by implanting hidden backdoor in a victim model, which adversaries can later exploit to trigger malicious behaviors during inference. However, current backdoor techniques are limited to static scenarios where attackers must define a malicious objective before training, locking the attack into a predetermined action without inference-time adaptability. Given the expressive output space in object detection, including object existence detection, bounding box estimation, and object classification, the feasibility of implanting a backdoor that provides inference-time control with a high degree of freedom remains unexplored. This paper introduces AnywhereDoor, a flexible backdoor attack tailored for object detection. Once implanted, AnywhereDoor enables adversaries to specify different attack types (object vanishing, fabrication, or misclassification) and configurations (untargeted or targeted with specific classes) to dynamically control detection behavior. This flexibility is achieved through three key innovations: (i) objective disentanglement to support a broader range of attack combinations well beyond what existing methods allow; (ii) trigger mosaicking to ensure backdoor activations are robust, even against those object detectors that extract localized regions from the input image for recognition; and (iii) strategic batching to address object-level data imbalances that otherwise hinders a balanced manipulation. Extensive experiments demonstrate that AnywhereDoor provides attackers with a high degree of control, achieving an attack success rate improvement of nearly 80% compared to adaptations of existing methods for such flexible control. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14243v1-abstract-full').style.display = 'none'; document.getElementById('2411.14243v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13867">arXiv:2411.13867</a> <span> [<a href="https://arxiv.org/pdf/2411.13867">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Generative Fuzzy System for Sequence Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+H">Hailong Yang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Z">Zhaohong Deng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhuangzhuang Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guanjin Wang</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+K">Kup-sze Choi</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="2411.13867v1-abstract-short" style="display: inline;"> Generative Models (GMs), particularly Large Language Models (LLMs), have garnered significant attention in machine learning and artificial intelligence for their ability to generate new data by learning the statistical properties of training data and creating data that resemble the original. This capability offers a wide range of applications across various domains. However, the complex structures… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13867v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13867v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13867v1-abstract-full" style="display: none;"> Generative Models (GMs), particularly Large Language Models (LLMs), have garnered significant attention in machine learning and artificial intelligence for their ability to generate new data by learning the statistical properties of training data and creating data that resemble the original. This capability offers a wide range of applications across various domains. However, the complex structures and numerous model parameters of GMs make the input-output processes opaque, complicating the understanding and control of outputs. Moreover, the purely data-driven learning mechanism limits GM's ability to acquire broader knowledge. There remains substantial potential for enhancing the robustness and generalization capabilities of GMs. In this work, we introduce the fuzzy system, a classical modeling method that combines data and knowledge-driven mechanisms, to generative tasks. We propose a novel Generative Fuzzy System framework, named GenFS, which integrates the deep learning capabilities of GM with the interpretability and dual-driven mechanisms of fuzzy systems. Specifically, we propose an end-to-end GenFS-based model for sequence generation, called FuzzyS2S. A series of experimental studies were conducted on 12 datasets, covering three distinct categories of generative tasks: machine translation, code generation, and summary generation. The results demonstrate that FuzzyS2S outperforms the Transformer in terms of accuracy and fluency. Furthermore, it exhibits better performance on some datasets compared to state-of-the-art models T5 and CodeT5. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13867v1-abstract-full').style.display = 'none'; document.getElementById('2411.13867v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 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/2411.13817">arXiv:2411.13817</a> <span> [<a href="https://arxiv.org/pdf/2411.13817">pdf</a>, <a href="https://arxiv.org/format/2411.13817">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> Dynamic Structural Clustering Unleashed: Flexible Similarities, Versatile Updates and for All Parameters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhuowei Zhao</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+J">Junhao Gan</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+B">Boyu Ruan</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+Z">Zhifeng Bao</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+J">Jianzhong Qi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sibo Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13817v1-abstract-short" style="display: inline;"> We study structural clustering on graphs in dynamic scenarios, where the graphs can be updated by arbitrary insertions or deletions of edges/vertices. The goal is to efficiently compute structural clustering results for any clustering parameters $蔚$ and $渭$ given on the fly, for arbitrary graph update patterns, and for all typical similarity measurements. Specifically, we adopt the idea of update… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13817v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13817v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13817v1-abstract-full" style="display: none;"> We study structural clustering on graphs in dynamic scenarios, where the graphs can be updated by arbitrary insertions or deletions of edges/vertices. The goal is to efficiently compute structural clustering results for any clustering parameters $蔚$ and $渭$ given on the fly, for arbitrary graph update patterns, and for all typical similarity measurements. Specifically, we adopt the idea of update affordability and propose an a-lot-simpler yet more efficient (both theoretically and practically) algorithm (than state of the art), named VD-STAR to handle graph updates. First, with a theoretical clustering result quality guarantee, VD-STAR can output high-quality clustering results with up to 99.9% accuracy. Second, our VD-STAR is easy to implement as it just needs to maintain certain sorted linked lists and hash tables, and hence, effectively enhances its deployment in practice. Third and most importantly, by careful analysis, VD-STAR improves the per-update time bound of the state-of-the-art from $O(\log^2 n)$ expected with certain update pattern assumption to $O(\log n)$ amortized in expectation without any update pattern assumption. We further design two variants of VD-STAR to enhance its empirical performance. Experimental results show that our algorithms consistently outperform the state-of-the-art competitors by up to 9,315 times in update time across nine real datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13817v1-abstract-full').style.display = 'none'; document.getElementById('2411.13817v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13784">arXiv:2411.13784</a> <span> [<a href="https://arxiv.org/pdf/2411.13784">pdf</a>, <a href="https://arxiv.org/format/2411.13784">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> </div> </div> <p class="title is-5 mathjax"> $d_X$-Privacy for Text and the Curse of Dimensionality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Asghar%2C+H+J">Hassan Jameel Asghar</a>, <a href="/search/cs?searchtype=author&query=Carpentier%2C+R">Robin Carpentier</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+B+Z+H">Benjamin Zi Hao Zhao</a>, <a href="/search/cs?searchtype=author&query=Kaafar%2C+D">Dali Kaafar</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="2411.13784v1-abstract-short" style="display: inline;"> A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for $d_X$-privacy, which is a relaxation of differential privacy for metric spaces. We identify an intriguing peculiarity of this mechanism. When applied on a word-by-word basis, the mechanism either outputs the original word, or completely dissimilar words, and very rarely any semantically s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13784v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13784v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13784v1-abstract-full" style="display: none;"> A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for $d_X$-privacy, which is a relaxation of differential privacy for metric spaces. We identify an intriguing peculiarity of this mechanism. When applied on a word-by-word basis, the mechanism either outputs the original word, or completely dissimilar words, and very rarely any semantically similar words. We investigate this observation in detail, and tie it to the fact that the distance of the nearest neighbor of a word in any word embedding model (which are high-dimensional) is much larger than the relative difference in distances to any of its two consecutive neighbors. We also show that the dot product of the multidimensional Laplace noise vector with any word embedding plays a crucial role in designating the nearest neighbor. We derive the distribution, moments and tail bounds of this dot product. We further propose a fix as a post-processing step, which satisfactorily removes the above-mentioned issue. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13784v1-abstract-full').style.display = 'none'; document.getElementById('2411.13784v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13577">arXiv:2411.13577</a> <span> [<a href="https://arxiv.org/pdf/2411.13577">pdf</a>, <a href="https://arxiv.org/format/2411.13577">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> WavChat: A Survey of Spoken Dialogue Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ji%2C+S">Shengpeng Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yifu Chen</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+M">Minghui Fang</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+J">Jialong Zuo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jingyu Lu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hanting Wang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Ziyue Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+L">Long Zhou</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shujie Liu</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xize Cheng</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xiaoda Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zehan Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Q">Qian Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jian Li</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yidi Jiang</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jingzhen He</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+Y">Yunfei Chu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jin Xu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhou Zhao</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="2411.13577v1-abstract-short" style="display: inline;"> Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that comprise speech recognition (ASR), large language models (LLMs), and text-to-speech (TTS), modern spoken dialogue models exhibit greater intelligence. These advanced spoken dialogue model… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13577v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13577v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13577v1-abstract-full" style="display: none;"> Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that comprise speech recognition (ASR), large language models (LLMs), and text-to-speech (TTS), modern spoken dialogue models exhibit greater intelligence. These advanced spoken dialogue models not only comprehend audio, music, and other speech-related features, but also capture stylistic and timbral characteristics in speech. Moreover, they generate high-quality, multi-turn speech responses with low latency, enabling real-time interaction through simultaneous listening and speaking capability. Despite the progress in spoken dialogue systems, there is a lack of comprehensive surveys that systematically organize and analyze these systems and the underlying technologies. To address this, we have first compiled existing spoken dialogue systems in the chronological order and categorized them into the cascaded and end-to-end paradigms. We then provide an in-depth overview of the core technologies in spoken dialogue models, covering aspects such as speech representation, training paradigm, streaming, duplex, and interaction capabilities. Each section discusses the limitations of these technologies and outlines considerations for future research. Additionally, we present a thorough review of relevant datasets, evaluation metrics, and benchmarks from the perspectives of training and evaluating spoken dialogue systems. We hope this survey will contribute to advancing both academic research and industrial applications in the field of spoken dialogue systems. The related material is available at https://github.com/jishengpeng/WavChat. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13577v1-abstract-full').style.display = 'none'; document.getElementById('2411.13577v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">60 papes, working in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13004">arXiv:2411.13004</a> <span> [<a href="https://arxiv.org/pdf/2411.13004">pdf</a>, <a href="https://arxiv.org/format/2411.13004">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuxuan Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Rongpeng Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhifeng Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Honggang Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13004v1-abstract-short" style="display: inline;"> We present MERLOT, a scalable mixture-of-expert (MoE) based refinement of distilled large language model optimized for encrypted traffic classification. By applying model distillation techniques in a teacher-student paradigm, compact models derived from GPT-2-base retain high classification accuracy while minimizing computational costs. These models function as specialized experts in an MoE archit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13004v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13004v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13004v1-abstract-full" style="display: none;"> We present MERLOT, a scalable mixture-of-expert (MoE) based refinement of distilled large language model optimized for encrypted traffic classification. By applying model distillation techniques in a teacher-student paradigm, compact models derived from GPT-2-base retain high classification accuracy while minimizing computational costs. These models function as specialized experts in an MoE architecture, dynamically assigned via a gating network. Unlike generation-based methods, our approach directly classifies encrypted traffic using the final decoder token with contextual feature embedding as input. Experiments on 10 datasets show superior or competitive performance over the state-of-the-art models while significantly reducing resource demands, underscoring its effectiveness and robustness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13004v1-abstract-full').style.display = 'none'; document.getElementById('2411.13004v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12556">arXiv:2411.12556</a> <span> [<a href="https://arxiv.org/pdf/2411.12556">pdf</a>, <a href="https://arxiv.org/format/2411.12556">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"> UMGAD: Unsupervised Multiplex Graph Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+J">Jianpeng Qi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhongying Zhao</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+G">Guanjie Zheng</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+L">Lei Cao</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Junyu Dong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yanwei Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12556v1-abstract-short" style="display: inline;"> Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority. This task is widely applied in various real-world scenarios, including fraud detection and social network analysis. However, existing GAD methods still face two major challenges: (1) They are often limited to detecting a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12556v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12556v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12556v1-abstract-full" style="display: none;"> Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority. This task is widely applied in various real-world scenarios, including fraud detection and social network analysis. However, existing GAD methods still face two major challenges: (1) They are often limited to detecting anomalies in single-type interaction graphs and struggle with multiple interaction types in multiplex heterogeneous graphs; (2) In unsupervised scenarios, selecting appropriate anomaly score thresholds remains a significant challenge for accurate anomaly detection. To address the above challenges, we propose a novel Unsupervised Multiplex Graph Anomaly Detection method, named UMGAD. We first learn multi-relational correlations among nodes in multiplex heterogeneous graphs and capture anomaly information during node attribute and structure reconstruction through graph-masked autoencoder (GMAE). Then, to further weaken the influence of noise and redundant information on abnormal information extraction, we generate attribute-level and subgraph-level augmented-view graphs respectively, and perform attribute and structure reconstruction through GMAE. Finally, We learn to optimize node attributes and structural features through contrastive learning between original-view and augmented-view graphs to improve the model's ability to capture anomalies. Meanwhile, we also propose a new anomaly score threshold selection strategy, which allows the model to be independent of the ground truth in real unsupervised scenarios. Extensive experiments on four datasets show that our \model significantly outperforms state-of-the-art methods, achieving average improvements of 13.48% in AUC and 11.68% in Macro-F1 across all datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12556v1-abstract-full').style.display = 'none'; document.getElementById('2411.12556v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11906">arXiv:2411.11906</a> <span> [<a href="https://arxiv.org/pdf/2411.11906">pdf</a>, <a href="https://arxiv.org/format/2411.11906">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"> $\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+P">Peizhe Xia</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+L">Long Peng</a>, <a href="/search/cs?searchtype=author&query=Di%2C+X">Xin Di</a>, <a href="/search/cs?searchtype=author&query=Pei%2C+R">Renjing Pei</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yang Wang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yang Cao</a>, <a href="/search/cs?searchtype=author&query=Zha%2C+Z">Zheng-Jun Zha</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="2411.11906v1-abstract-short" style="display: inline;"> Arbitrary scale super-resolution (ASSR) aims to super-resolve low-resolution images to high-resolution images at any scale using a single model, addressing the limitations of traditional super-resolution methods that are restricted to fixed-scale factors (e.g., $\times2$, $\times4$). The advent of Implicit Neural Representations (INR) has brought forth a plethora of novel methodologies for ASSR, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11906v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11906v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11906v1-abstract-full" style="display: none;"> Arbitrary scale super-resolution (ASSR) aims to super-resolve low-resolution images to high-resolution images at any scale using a single model, addressing the limitations of traditional super-resolution methods that are restricted to fixed-scale factors (e.g., $\times2$, $\times4$). The advent of Implicit Neural Representations (INR) has brought forth a plethora of novel methodologies for ASSR, which facilitate the reconstruction of original continuous signals by modeling a continuous representation space for coordinates and pixel values, thereby enabling arbitrary-scale super-resolution. Consequently, the primary objective of ASSR is to construct a continuous representation space derived from low-resolution inputs. However, existing methods, primarily based on CNNs and Transformers, face significant challenges such as high computational complexity and inadequate modeling of long-range dependencies, which hinder their effectiveness in real-world applications. To overcome these limitations, we propose a novel arbitrary-scale super-resolution method, called $\text{S}^{3}$Mamba, to construct a scalable continuous representation space. Specifically, we propose a Scalable State Space Model (SSSM) to modulate the state transition matrix and the sampling matrix of step size during the discretization process, achieving scalable and continuous representation modeling with linear computational complexity. Additionally, we propose a novel scale-aware self-attention mechanism to further enhance the network's ability to perceive global important features at different scales, thereby building the $\text{S}^{3}$Mamba to achieve superior arbitrary-scale super-resolution. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our method achieves state-of-the-art performance and superior generalization capabilities at arbitrary super-resolution scales. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11906v1-abstract-full').style.display = 'none'; document.getElementById('2411.11906v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11521">arXiv:2411.11521</a> <span> [<a href="https://arxiv.org/pdf/2411.11521">pdf</a>, <a href="https://arxiv.org/format/2411.11521">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Carpentier%2C+R">Robin Carpentier</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+B+Z+H">Benjamin Zi Hao Zhao</a>, <a href="/search/cs?searchtype=author&query=Asghar%2C+H+J">Hassan Jameel Asghar</a>, <a href="/search/cs?searchtype=author&query=Kaafar%2C+D">Dali Kaafar</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="2411.11521v1-abstract-short" style="display: inline;"> Individuals have been increasingly interacting with online Large Language Models (LLMs), both in their work and personal lives. These interactions raise privacy issues as the LLMs are typically hosted by third-parties who can gather a variety of sensitive information about users and their companies. Text Sanitization techniques have been proposed in the literature and can be used to sanitize user… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11521v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11521v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11521v1-abstract-full" style="display: none;"> Individuals have been increasingly interacting with online Large Language Models (LLMs), both in their work and personal lives. These interactions raise privacy issues as the LLMs are typically hosted by third-parties who can gather a variety of sensitive information about users and their companies. Text Sanitization techniques have been proposed in the literature and can be used to sanitize user prompts before sending them to the LLM. However, sanitization has an impact on the downstream task performed by the LLM, and often to such an extent that it leads to unacceptable results for the user. This is not just a minor annoyance, with clear monetary consequences as LLM services charge on a per use basis as well as great amount of computing resources wasted. We propose an architecture leveraging a Small Language Model (SLM) at the user-side to help estimate the impact of sanitization on a prompt before it is sent to the LLM, thus preventing resource losses. Our evaluation of this architecture revealed a significant problem with text sanitization based on Differential Privacy, on which we want to draw the attention of the community for further investigation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11521v1-abstract-full').style.display = 'none'; document.getElementById('2411.11521v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11508">arXiv:2411.11508</a> <span> [<a href="https://arxiv.org/pdf/2411.11508">pdf</a>, <a href="https://arxiv.org/format/2411.11508">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Collaborative Contrastive Network for Click-Through Rate Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+C">Chen Gao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zixin Zhao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Sihao Hu</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+L">Lv Shao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tong Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11508v1-abstract-short" style="display: inline;"> E-commerce platforms provide entrances for customers to enter mini-apps to meet their specific shopping needs. At the entrance of a mini-app, a trigger item recommended based on customers' historical preferences, is displayed to attract customers to enter the mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion of customer entries is driv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11508v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11508v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11508v1-abstract-full" style="display: none;"> E-commerce platforms provide entrances for customers to enter mini-apps to meet their specific shopping needs. At the entrance of a mini-app, a trigger item recommended based on customers' historical preferences, is displayed to attract customers to enter the mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion of customer entries is driven by their interest in the mini-app itself rather than the trigger item. In such cases, approaches highly hinging on the trigger item tend to recommend similar items, thus misunderstanding the customers' real intention; (ii) Approaches that consider customers' intention toward mini-apps, require the regular existence of mini-apps for customers to cultivate routine shopping habits, making such approaches less robust for mini-apps that are available for only short periods (1 or 3 days) in Explosive Promotional Scenarios (EPS), such as the Black Friday and China's Double 11 Shopping Carnival. To address the above-mentioned issues, we introduce a more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN). Given a user, CCN learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning. This paradigm does not need to explicitly estimate user's binary entry intention and avoids amplifying the impact of the trigger item. Online A/B testing on large-scale real-world data demonstrates that CCN sets a new state-of-the-art performance on Taobao, boosting CTR by 12.3% and order volume by 12.7%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11508v1-abstract-full').style.display = 'none'; document.getElementById('2411.11508v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11502">arXiv:2411.11502</a> <span> [<a href="https://arxiv.org/pdf/2411.11502">pdf</a>, <a href="https://arxiv.org/format/2411.11502">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> All-domain Moveline Evolution Network for Click-Through Rate Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+C">Chen Gao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zixin Zhao</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+L">Lv Shao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tong Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11502v1-abstract-short" style="display: inline;"> E-commerce app users exhibit behaviors that are inherently logically consistent. A series of multi-scenario user behaviors interconnect to form the scene-level all-domain user moveline, which ultimately reveals the user's true intention. Traditional CTR prediction methods typically focus on the item-level interaction between the target item and the historically interacted items. However, the scene… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11502v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11502v1-abstract-full" style="display: none;"> E-commerce app users exhibit behaviors that are inherently logically consistent. A series of multi-scenario user behaviors interconnect to form the scene-level all-domain user moveline, which ultimately reveals the user's true intention. Traditional CTR prediction methods typically focus on the item-level interaction between the target item and the historically interacted items. However, the scene-level interaction between the target item and the user moveline remains underexplored. There are two challenges when modeling the interaction with preceding all-domain user moveline: (i) Heterogeneity between items and scenes: Unlike traditional user behavior sequences that utilize items as carriers, the user moveline utilizes scenes as carriers. The heterogeneity between items and scenes complicates the process of aligning interactions within a unified representation space. (ii) Temporal misalignment of linked scene-level and item-level behaviors: In the preceding user moveline with a fixed sampling length, certain critical scene-level behaviors are closely linked to subsequent item-level behaviors. However, it is impossible to establish a complete temporal alignment that clearly identifies which specific scene-level behaviors correspond to which item-level behaviors. To address these challenges and pioneer modeling user intent from the perspective of the all-domain moveline, we propose All-domain Moveline Evolution Network (AMEN). AMEN not only transfers interactions between items and scenes to homogeneous representation spaces, but also introduces a Temporal Sequential Pairwise (TSP) mechanism to understand the nuanced associations between scene-level and item-level behaviors, ensuring that the all-domain user moveline differentially influences CTR predictions for user's favored and unfavored items. Online A/B testing demonstrates that our method achieves a +11.6% increase in CTCVR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11502v1-abstract-full').style.display = 'none'; document.getElementById('2411.11502v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10798">arXiv:2411.10798</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Peng%2C+L">Long Peng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenbo Li</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jiaming Guo</a>, <a href="/search/cs?searchtype=author&query=Di%2C+X">Xin Di</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Haoze Sun</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yong Li</a>, <a href="/search/cs?searchtype=author&query=Pei%2C+R">Renjing Pei</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yang Wang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yang Cao</a>, <a href="/search/cs?searchtype=author&query=Zha%2C+Z">Zheng-Jun Zha</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="2411.10798v2-abstract-short" style="display: inline;"> Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB domain, often leading to a lack of richness or fidelity in fine details. In this paper, we pioneer the use of details hidden in RAW data to complement existing RGB-on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10798v2-abstract-full').style.display = 'inline'; document.getElementById('2411.10798v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10798v2-abstract-full" style="display: none;"> Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB domain, often leading to a lack of richness or fidelity in fine details. In this paper, we pioneer the use of details hidden in RAW data to complement existing RGB-only methods, yielding superior outputs. We argue that key image processing steps in Image Signal Processing, such as denoising and demosaicing, inherently result in the loss of fine details in LR images, making LR RAW a valuable information source. To validate this, we present RealSR-RAW, a comprehensive dataset comprising over 10,000 pairs with LR and HR RGB images, along with corresponding LR RAW, captured across multiple smartphones under varying focal lengths and diverse scenes. Additionally, we propose a novel, general RAW adapter to efficiently integrate LR RAW data into existing CNNs, Transformers, and Diffusion-based Real SR models by suppressing the noise contained in LR RAW and aligning its distribution. Extensive experiments demonstrate that incorporating RAW data significantly enhances detail recovery and improves Real SR performance across ten evaluation metrics, including both fidelity and perception-oriented metrics. Our findings open a new direction for the Real SR task, with the dataset and code will be made available to support future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10798v2-abstract-full').style.display = 'none'; document.getElementById('2411.10798v2-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 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">We sincerely apologize, but due to some commercial confidentiality agreements related to the report, we have decided to withdraw the submission for now and will resubmit after making the necessary revisions</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09625">arXiv:2411.09625</a> <span> [<a href="https://arxiv.org/pdf/2411.09625">pdf</a>, <a href="https://arxiv.org/format/2411.09625">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Local deployment of large-scale music AI models on commodity hardware </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xun Zhou</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+C">Charlie Ruan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihe Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tianqi Chen</a>, <a href="/search/cs?searchtype=author&query=Donahue%2C+C">Chris Donahue</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="2411.09625v1-abstract-short" style="display: inline;"> We present the MIDInfinite, a web application capable of generating symbolic music using a large-scale generative AI model locally on commodity hardware. Creating this demo involved porting the Anticipatory Music Transformer, a large language model (LLM) pre-trained on the Lakh MIDI dataset, to the Machine Learning Compilation (MLC) framework. Once the model is ported, MLC facilitates inference on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09625v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09625v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09625v1-abstract-full" style="display: none;"> We present the MIDInfinite, a web application capable of generating symbolic music using a large-scale generative AI model locally on commodity hardware. Creating this demo involved porting the Anticipatory Music Transformer, a large language model (LLM) pre-trained on the Lakh MIDI dataset, to the Machine Learning Compilation (MLC) framework. Once the model is ported, MLC facilitates inference on a variety of runtimes including C++, mobile, and the browser. We envision that MLC has the potential to bridge the gap between the landscape of increasingly capable music AI models and technology more familiar to music software developers. As a proof of concept, we build a web application that allows users to generate endless streams of multi-instrumental MIDI in the browser, either from scratch or conditioned on a prompt. On commodity hardware (an M3 Macbook Pro), our demo can generate 51 notes per second, which is faster than real-time playback for 72.9% of generations, and increases to 86.3% with 2 seconds of upfront buffering. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09625v1-abstract-full').style.display = 'none'; document.getElementById('2411.09625v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">2 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09484">arXiv:2411.09484</a> <span> [<a href="https://arxiv.org/pdf/2411.09484">pdf</a>, <a href="https://arxiv.org/format/2411.09484">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"> Image Matching Filtering and Refinement by Planes and Beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bellavia%2C+F">Fabio Bellavia</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhenjun Zhao</a>, <a href="/search/cs?searchtype=author&query=Morelli%2C+L">Luca Morelli</a>, <a href="/search/cs?searchtype=author&query=Remondino%2C+F">Fabio Remondino</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="2411.09484v2-abstract-short" style="display: inline;"> This paper introduces a modular, non-deep learning method for filtering and refining sparse correspondences in image matching. Assuming that motion flow within the scene can be approximated by local homography transformations, matches are aggregated into overlapping clusters corresponding to virtual planes using an iterative RANSAC-based approach, with non-conforming correspondences discarded. Mor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09484v2-abstract-full').style.display = 'inline'; document.getElementById('2411.09484v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09484v2-abstract-full" style="display: none;"> This paper introduces a modular, non-deep learning method for filtering and refining sparse correspondences in image matching. Assuming that motion flow within the scene can be approximated by local homography transformations, matches are aggregated into overlapping clusters corresponding to virtual planes using an iterative RANSAC-based approach, with non-conforming correspondences discarded. Moreover, the underlying planar structural design provides an explicit map between local patches associated with the matches, enabling optional refinement of keypoint positions through cross-correlation template matching after patch reprojection. Finally, to enhance robustness and fault-tolerance against violations of the piece-wise planar approximation assumption, a further strategy is designed for minimizing relative patch distortion in the plane reprojection by introducing an intermediate homography that projects both patches into a common plane. The proposed method is extensively evaluated on standard datasets and image matching pipelines, and compared with state-of-the-art approaches. Unlike other current comparisons, the proposed benchmark also takes into account the more general, real, and practical cases where camera intrinsics are unavailable. Experimental results demonstrate that our proposed non-deep learning, geometry-based approach achieves performances that are either superior to or on par with recent state-of-the-art deep learning methods. Finally, this study suggests that there are still development potential in actual image matching solutions in the considered research direction, which could be in the future incorporated in novel deep image matching architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09484v2-abstract-full').style.display = 'none'; document.getElementById('2411.09484v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">project page: https://github.com/fb82/MiHo</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08641">arXiv:2411.08641</a> <span> [<a href="https://arxiv.org/pdf/2411.08641">pdf</a>, <a href="https://arxiv.org/format/2411.08641">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DipMe: Haptic Recognition of Granular Media for Tangible Interactive Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinkai Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shuo Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziyi Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Lifeng Zhu</a>, <a href="/search/cs?searchtype=author&query=Song%2C+A">Aiguo Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08641v1-abstract-short" style="display: inline;"> While tangible user interface has shown its power in naturally interacting with rigid or soft objects, users cannot conveniently use different types of granular materials as the interaction media. We introduce DipMe as a smart device to recognize the types of granular media in real time, which can be used to connect the granular materials in the physical world with various virtual content. Other t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08641v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08641v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08641v1-abstract-full" style="display: none;"> While tangible user interface has shown its power in naturally interacting with rigid or soft objects, users cannot conveniently use different types of granular materials as the interaction media. We introduce DipMe as a smart device to recognize the types of granular media in real time, which can be used to connect the granular materials in the physical world with various virtual content. Other than vision-based solutions, we propose a dip operation of our device and exploit the haptic signals to recognize different types of granular materials. With modern machine learning tools, we find the haptic signals from different granular media are distinguishable by DipMe. With the online granular object recognition, we build several tangible interactive applications, demonstrating the effects of DipMe in perceiving granular materials and its potential in developing a tangible user interface with granular objects as the new media. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08641v1-abstract-full').style.display = 'none'; document.getElementById('2411.08641v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08014">arXiv:2411.08014</a> <span> [<a href="https://arxiv.org/pdf/2411.08014">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Artistic Neural Style Transfer Algorithms with Activation Smoothing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiangtian Li</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+H">Han Cao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jiacheng Hu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Y">Yuhui Jin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihao Zhao</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="2411.08014v1-abstract-short" style="display: inline;"> The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images. This process of transferring content images in different styles is called Neural Style Transfer (NST). In this paper, we re-implement image-based NST, fast NST, and arbitrary NST. We also explore to utilize ResNet with activation smoothing in NST. Extensive experimental… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08014v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08014v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08014v1-abstract-full" style="display: none;"> The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images. This process of transferring content images in different styles is called Neural Style Transfer (NST). In this paper, we re-implement image-based NST, fast NST, and arbitrary NST. We also explore to utilize ResNet with activation smoothing in NST. Extensive experimental results demonstrate that smoothing transformation can greatly improve the quality of stylization results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08014v1-abstract-full').style.display = 'none'; document.getElementById('2411.08014v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages,7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07597">arXiv:2411.07597</a> <span> [<a href="https://arxiv.org/pdf/2411.07597">pdf</a>, <a href="https://arxiv.org/format/2411.07597">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> </div> </div> <p class="title is-5 mathjax"> A Survey on Adversarial Machine Learning for Code Data: Realistic Threats, Countermeasures, and Interpretations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yulong Yang</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+H">Haoran Fan</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chenhao Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhengyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chao Shen</a>, <a href="/search/cs?searchtype=author&query=Guan%2C+X">Xiaohong Guan</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="2411.07597v1-abstract-short" style="display: inline;"> Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent years. However, in realistic scenarios, CLMs are exposed to potential malicious adversaries, bringing risks to the confidentiality, integrity, and availability o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07597v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07597v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07597v1-abstract-full" style="display: none;"> Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent years. However, in realistic scenarios, CLMs are exposed to potential malicious adversaries, bringing risks to the confidentiality, integrity, and availability of CLM systems. Despite these risks, a comprehensive analysis of the security vulnerabilities of CLMs in the extremely adversarial environment has been lacking. To close this research gap, we categorize existing attack techniques into three types based on the CIA triad: poisoning attacks (integrity \& availability infringement), evasion attacks (integrity infringement), and privacy attacks (confidentiality infringement). We have collected so far the most comprehensive (79) papers related to adversarial machine learning for CLM from the research fields of artificial intelligence, computer security, and software engineering. Our analysis covers each type of risk, examining threat model categorization, attack techniques, and countermeasures, while also introducing novel perspectives on eXplainable AI (XAI) and exploring the interconnections between different risks. Finally, we identify current challenges and future research opportunities. This study aims to provide a comprehensive roadmap for both researchers and practitioners and pave the way towards more reliable CLMs for practical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07597v1-abstract-full').style.display = 'none'; document.getElementById('2411.07597v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under a reviewing process since Sep. 3, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07547">arXiv:2411.07547</a> <span> [<a href="https://arxiv.org/pdf/2411.07547">pdf</a>, <a href="https://arxiv.org/format/2411.07547">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pingjie Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihan Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+L">Liudan Zhao</a>, <a href="/search/cs?searchtype=author&query=He%2C+M">Miao He</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xin Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Ya Zhang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+K">Kun Sun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanfeng Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07547v1-abstract-short" style="display: inline;"> Auscultation of internal body sounds is essential for diagnosing a range of health conditions, yet its effectiveness is often limited by clinicians' expertise and the acoustic constraints of human hearing, restricting its use across various clinical scenarios. To address these challenges, we introduce AuscultaBase, a foundational framework aimed at advancing body sound diagnostics through innovati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07547v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07547v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07547v1-abstract-full" style="display: none;"> Auscultation of internal body sounds is essential for diagnosing a range of health conditions, yet its effectiveness is often limited by clinicians' expertise and the acoustic constraints of human hearing, restricting its use across various clinical scenarios. To address these challenges, we introduce AuscultaBase, a foundational framework aimed at advancing body sound diagnostics through innovative data integration and contrastive learning techniques. Our contributions include the following: First, we compile AuscultaBase-Corpus, a large-scale, multi-source body sound database encompassing 11 datasets with 40,317 audio recordings and totaling 322.4 hours of heart, lung, and bowel sounds. Second, we develop AuscultaBase-Model, a foundational diagnostic model for body sounds, utilizing contrastive learning on the compiled corpus. Third, we establish AuscultaBase-Bench, a comprehensive benchmark containing 16 sub-tasks, assessing the performance of various open-source acoustic pre-trained models. Evaluation results indicate that our model outperforms all other open-source models in 12 out of 16 tasks, demonstrating the efficacy of our approach in advancing diagnostic capabilities for body sound analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07547v1-abstract-full').style.display = 'none'; document.getElementById('2411.07547v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07025">arXiv:2411.07025</a> <span> [<a href="https://arxiv.org/pdf/2411.07025">pdf</a>, <a href="https://arxiv.org/format/2411.07025">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</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"> Scaling Mesh Generation via Compressive Tokenization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weng%2C+H">Haohan Weng</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zibo Zhao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+B">Biwen Lei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xianghui Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jian Liu</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+Z">Zeqiang Lai</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuhong Liu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jie Jiang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+C">Chunchao Guo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tong Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shenghua Gao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C+L+P">C. L. Philip Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07025v1-abstract-short" style="display: inline;"> We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data wit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07025v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07025v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07025v1-abstract-full" style="display: none;"> We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07025v1-abstract-full').style.display = 'none'; document.getElementById('2411.07025v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Homepage: https://whaohan.github.io/bpt , Code: https://github.com/whaohan/bpt</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06449">arXiv:2411.06449</a> <span> [<a href="https://arxiv.org/pdf/2411.06449">pdf</a>, <a href="https://arxiv.org/format/2411.06449">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Improved Video VAE for Latent Video Diffusion Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+P">Pingyu Wu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+K">Kai Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yu Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+L">Liming Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+W">Wei Zhai</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yang Cao</a>, <a href="/search/cs?searchtype=author&query=Zha%2C+Z">Zheng-Jun Zha</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="2411.06449v1-abstract-short" style="display: inline;"> Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a pretrained image VAE into the 3D causal structure for temporal-spatial compression, this paper presents two astonishing findings: (1) The initialization from a well-tra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06449v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06449v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06449v1-abstract-full" style="display: none;"> Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a pretrained image VAE into the 3D causal structure for temporal-spatial compression, this paper presents two astonishing findings: (1) The initialization from a well-trained image VAE with the same latent dimensions suppresses the improvement of subsequent temporal compression capabilities. (2) The adoption of causal reasoning leads to unequal information interactions and unbalanced performance between frames. To alleviate these problems, we propose a keyframe-based temporal compression (KTC) architecture and a group causal convolution (GCConv) module to further improve video VAE (IV-VAE). Specifically, the KTC architecture divides the latent space into two branches, in which one half completely inherits the compression prior of keyframes from a lower-dimension image VAE while the other half involves temporal compression through 3D group causal convolution, reducing temporal-spatial conflicts and accelerating the convergence speed of video VAE. The GCConv in above 3D half uses standard convolution within each frame group to ensure inter-frame equivalence, and employs causal logical padding between groups to maintain flexibility in processing variable frame video. Extensive experiments on five benchmarks demonstrate the SOTA video reconstruction and generation capabilities of the proposed IV-VAE (https://wpy1999.github.io/IV-VAE/). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06449v1-abstract-full').style.display = 'none'; document.getElementById('2411.06449v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06171">arXiv:2411.06171</a> <span> [<a href="https://arxiv.org/pdf/2411.06171">pdf</a>, <a href="https://arxiv.org/format/2411.06171">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"> SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+J">Jinghan He</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Haiyun Guo</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+K">Kuan Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihan Zhao</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+M">Ming Tang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jinqiao Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06171v1-abstract-short" style="display: inline;"> Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the subsequent data-replay-based distillation can further enhance the performance. However, existing methods fail to fully exploit the knowledge embedded in models from… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06171v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06171v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06171v1-abstract-full" style="display: none;"> Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the subsequent data-replay-based distillation can further enhance the performance. However, existing methods fail to fully exploit the knowledge embedded in models from previous tasks, resulting in the need for a relatively large number of replay samples to achieve good results. In this work, we first explore and emphasize the importance of attention weights in knowledge retention, and then propose a SElective attEntion-guided Knowledge Retention method (SEEKR) for data-efficient replay-based continual learning of large language models (LLMs). Specifically, SEEKR performs attention distillation on the selected attention heads for finer-grained knowledge retention, where the proposed forgettability-based and task-sensitivity-based measures are used to identify the most valuable attention heads. Experimental results on two continual learning benchmarks for LLMs demonstrate the superiority of SEEKR over the existing methods on both performance and efficiency. Explicitly, SEEKR achieves comparable or even better performance with only 1/10 of the replayed data used by other methods, and reduces the proportion of replayed data to 1%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06171v1-abstract-full').style.display = 'none'; document.getElementById('2411.06171v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">EMNLP2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06111">arXiv:2411.06111</a> <span> [<a href="https://arxiv.org/pdf/2411.06111">pdf</a>, <a href="https://arxiv.org/format/2411.06111">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Energy-efficient Hybrid Model Predictive Trajectory Planning for Autonomous Electric Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ding%2C+F">Fan Ding</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+X">Xuewen Luo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Gaoxuan Li</a>, <a href="/search/cs?searchtype=author&query=Tew%2C+H+H">Hwa Hui Tew</a>, <a href="/search/cs?searchtype=author&query=Loo%2C+J+Y">Junn Yong Loo</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+C+W">Chor Wai Tong</a>, <a href="/search/cs?searchtype=author&query=Bakibillah%2C+A+S+M">A. S. M Bakibillah</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziyuan Zhao</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhiyu Tao</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="2411.06111v1-abstract-short" style="display: inline;"> To tackle the twin challenges of limited battery life and lengthy charging durations in electric vehicles (EVs), this paper introduces an Energy-efficient Hybrid Model Predictive Planner (EHMPP), which employs an energy-saving optimization strategy. EHMPP focuses on refining the design of the motion planner to be seamlessly integrated with the existing automatic driving algorithms, without additio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06111v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06111v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06111v1-abstract-full" style="display: none;"> To tackle the twin challenges of limited battery life and lengthy charging durations in electric vehicles (EVs), this paper introduces an Energy-efficient Hybrid Model Predictive Planner (EHMPP), which employs an energy-saving optimization strategy. EHMPP focuses on refining the design of the motion planner to be seamlessly integrated with the existing automatic driving algorithms, without additional hardware. It has been validated through simulation experiments on the Prescan, CarSim, and Matlab platforms, demonstrating that it can increase passive recovery energy by 11.74\% and effectively track motor speed and acceleration at optimal power. To sum up, EHMPP not only aids in trajectory planning but also significantly boosts energy efficiency in autonomous EVs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06111v1-abstract-full').style.display = 'none'; document.getElementById('2411.06111v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at the IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04954">arXiv:2411.04954</a> <span> [<a href="https://arxiv.org/pdf/2411.04954">pdf</a>, <a href="https://arxiv.org/format/2411.04954">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"> CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jingwei Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chenyu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zibo Zhao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wen Liu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yi Ma</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shenghua Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04954v1-abstract-short" style="display: inline;"> This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04954v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04954v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04954v1-abstract-full" style="display: none;"> This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within the CAD-MLLM framework, we leverage the command sequences of CAD models and then employ advanced large language models (LLMs) to align the feature space across these diverse multi-modalities data and CAD models' vectorized representations. To facilitate the model training, we design a comprehensive data construction and annotation pipeline that equips each CAD model with corresponding multimodal data. Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model. It contains approximately 450K instances and their CAD construction sequences. To thoroughly evaluate the quality of our generated CAD models, we go beyond current evaluation metrics that focus on reconstruction quality by introducing additional metrics that assess topology quality and surface enclosure extent. Extensive experimental results demonstrate that CAD-MLLM significantly outperforms existing conditional generative methods and remains highly robust to noises and missing points. The project page and more visualizations can be found at: https://cad-mllm.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04954v1-abstract-full').style.display = 'none'; document.getElementById('2411.04954v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project page: https://cad-mllm.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03603">arXiv:2411.03603</a> <span> [<a href="https://arxiv.org/pdf/2411.03603">pdf</a>, <a href="https://arxiv.org/format/2411.03603">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Yuqian Fu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuanheng Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoran Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zijie Zhao</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+J">Jiajun Chai</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+D">Dongbin Zhao</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="2411.03603v1-abstract-short" style="display: inline;"> Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy, existing methods are prone to falling into the local optima, hindering the effective exploration of better policies. Furthermore, tackling multi-agent tasks in complex environments requires cooperation during explorati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03603v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03603v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03603v1-abstract-full" style="display: none;"> Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy, existing methods are prone to falling into the local optima, hindering the effective exploration of better policies. Furthermore, tackling multi-agent tasks in complex environments requires cooperation during exploration, posing substantial challenges for MARL methods. To address these issues, we propose a Consistency Policy with consEnsus Guidance (CPEG), with two primary components: (a) introducing a multimodal policy to enhance exploration capabilities, and (b) sharing the consensus among agents to foster agent cooperation. For component (a), CPEG incorporates a Consistency model as the policy, leveraging its multimodal nature and stochastic characteristics to facilitate exploration. Regarding component (b), CPEG introduces a Consensus Learner to deduce the consensus on the global state from local observations. This consensus then serves as a guidance for the Consistency Policy, promoting cooperation among agents. The proposed method is evaluated in multi-agent particle environments (MPE) and multi-agent MuJoCo (MAMuJoCo), and empirical results indicate that CPEG not only achieves improvements in sparse-reward settings but also matches the performance of baselines in dense-reward environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03603v1-abstract-full').style.display = 'none'; document.getElementById('2411.03603v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02622">arXiv:2411.02622</a> <span> [<a href="https://arxiv.org/pdf/2411.02622">pdf</a>, <a href="https://arxiv.org/format/2411.02622">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"> Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihao Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yijiang Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yuchen Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Vasconcelos%2C+N">Nuno Vasconcelos</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yinzhi 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="2411.02622v1-abstract-short" style="display: inline;"> Machine unlearning--enabling a trained model to forget specific data--is crucial for addressing biased data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten". Recent works have paid little attention to privacy concerns, leaving the data intended for forgetting vulnerable to membership inference attacks. Moreover, they often come with h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02622v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02622v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02622v1-abstract-full" style="display: none;"> Machine unlearning--enabling a trained model to forget specific data--is crucial for addressing biased data and adhering to privacy regulations like the General Data Protection Regulation (GDPR)'s "right to be forgotten". Recent works have paid little attention to privacy concerns, leaving the data intended for forgetting vulnerable to membership inference attacks. Moreover, they often come with high computational overhead. In this work, we propose Pseudo-Probability Unlearning (PPU), a novel method that enables models to forget data efficiently and in a privacy-preserving manner. Our method replaces the final-layer output probabilities of the neural network with pseudo-probabilities for the data to be forgotten. These pseudo-probabilities follow either a uniform distribution or align with the model's overall distribution, enhancing privacy and reducing risk of membership inference attacks. Our optimization strategy further refines the predictive probability distributions and updates the model's weights accordingly, ensuring effective forgetting with minimal impact on the model's overall performance. Through comprehensive experiments on multiple benchmarks, our method achieves over 20% improvements in forgetting error compared to the state-of-the-art. Additionally, our method enhances privacy by preventing the forgotten set from being inferred to around random guesses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02622v1-abstract-full').style.display = 'none'; document.getElementById('2411.02622v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02265">arXiv:2411.02265</a> <span> [<a href="https://arxiv.org/pdf/2411.02265">pdf</a>, <a href="https://arxiv.org/format/2411.02265">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xingwu Sun</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yanfeng Chen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yiqing Huang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+R">Ruobing Xie</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jiaqi Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuaipeng Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhen Yang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jonny Han</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+X">Xiaobo Shu</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jiahao Bu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhongzhi Chen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xuemeng Huang</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+F">Fengzong Lian</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Saiyong Yang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+J">Jianfeng Yan</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+Y">Yuyuan Zeng</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiaoqin Ren</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+C">Chao Yu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L">Lulu Wu</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Y">Yue Mao</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+J">Jun Xia</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+T">Tao Yang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Suncong Zheng</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+K">Kan Wu</a> , et al. (83 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02265v3-abstract-short" style="display: inline;"> In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02265v3-abstract-full').style.display = 'inline'; document.getElementById('2411.02265v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02265v3-abstract-full" style="display: none;"> In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02265v3-abstract-full').style.display = 'none'; document.getElementById('2411.02265v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 4 Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02118">arXiv:2411.02118</a> <span> [<a href="https://arxiv.org/pdf/2411.02118">pdf</a>, <a href="https://arxiv.org/format/2411.02118">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Grounding Emotional Descriptions to Electrovibration Haptic Signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+G">Guimin Hu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zirui Zhao</a>, <a href="/search/cs?searchtype=author&query=Heilmann%2C+L">Lukas Heilmann</a>, <a href="/search/cs?searchtype=author&query=Vardar%2C+Y">Yasemin Vardar</a>, <a href="/search/cs?searchtype=author&query=Seifi%2C+H">Hasti Seifi</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="2411.02118v1-abstract-short" style="display: inline;"> Designing and displaying haptic signals with sensory and emotional attributes can improve the user experience in various applications. Free-form user language provides rich sensory and emotional information for haptic design (e.g., ``This signal feels smooth and exciting''), but little work exists on linking user descriptions to haptic signals (i.e., language grounding). To address this gap, we co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02118v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02118v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02118v1-abstract-full" style="display: none;"> Designing and displaying haptic signals with sensory and emotional attributes can improve the user experience in various applications. Free-form user language provides rich sensory and emotional information for haptic design (e.g., ``This signal feels smooth and exciting''), but little work exists on linking user descriptions to haptic signals (i.e., language grounding). To address this gap, we conducted a study where 12 users described the feel of 32 signals perceived on a surface haptics (i.e., electrovibration) display. We developed a computational pipeline using natural language processing (NLP) techniques, such as GPT-3.5 Turbo and word embedding methods, to extract sensory and emotional keywords and group them into semantic clusters (i.e., concepts). We linked the keyword clusters to haptic signal features (e.g., pulse count) using correlation analysis. The proposed pipeline demonstrates the viability of a computational approach to analyzing haptic experiences. We discuss our future plans for creating a predictive model of haptic experience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02118v1-abstract-full').style.display = 'none'; document.getElementById('2411.02118v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01915">arXiv:2411.01915</a> <span> [<a href="https://arxiv.org/pdf/2411.01915">pdf</a>, <a href="https://arxiv.org/format/2411.01915">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> RoboCrowd: Scaling Robot Data Collection through Crowdsourcing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mirchandani%2C+S">Suvir Mirchandani</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+D+D">David D. Yuan</a>, <a href="/search/cs?searchtype=author&query=Burns%2C+K">Kaylee Burns</a>, <a href="/search/cs?searchtype=author&query=Islam%2C+M+S">Md Sazzad Islam</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T+Z">Tony Z. Zhao</a>, <a href="/search/cs?searchtype=author&query=Finn%2C+C">Chelsea Finn</a>, <a href="/search/cs?searchtype=author&query=Sadigh%2C+D">Dorsa Sadigh</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="2411.01915v1-abstract-short" style="display: inline;"> In recent years, imitation learning from large-scale human demonstrations has emerged as a promising paradigm for training robot policies. However, the burden of collecting large quantities of human demonstrations is significant in terms of collection time and the need for access to expert operators. We introduce a new data collection paradigm, RoboCrowd, which distributes the workload by utilizin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01915v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01915v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01915v1-abstract-full" style="display: none;"> In recent years, imitation learning from large-scale human demonstrations has emerged as a promising paradigm for training robot policies. However, the burden of collecting large quantities of human demonstrations is significant in terms of collection time and the need for access to expert operators. We introduce a new data collection paradigm, RoboCrowd, which distributes the workload by utilizing crowdsourcing principles and incentive design. RoboCrowd helps enable scalable data collection and facilitates more efficient learning of robot policies. We build RoboCrowd on top of ALOHA (Zhao et al. 2023) -- a bimanual platform that supports data collection via puppeteering -- to explore the design space for crowdsourcing in-person demonstrations in a public environment. We propose three classes of incentive mechanisms to appeal to users' varying sources of motivation for interacting with the system: material rewards, intrinsic interest, and social comparison. We instantiate these incentives through tasks that include physical rewards, engaging or challenging manipulations, as well as gamification elements such as a leaderboard. We conduct a large-scale, two-week field experiment in which the platform is situated in a university cafe. We observe significant engagement with the system -- over 200 individuals independently volunteered to provide a total of over 800 interaction episodes. Our findings validate the proposed incentives as mechanisms for shaping users' data quantity and quality. Further, we demonstrate that the crowdsourced data can serve as useful pre-training data for policies fine-tuned on expert demonstrations -- boosting performance up to 20% compared to when this data is not available. These results suggest the potential for RoboCrowd to reduce the burden of robot data collection by carefully implementing crowdsourcing and incentive design principles. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01915v1-abstract-full').style.display = 'none'; document.getElementById('2411.01915v1-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">21 pages, 25 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01805">arXiv:2411.01805</a> <span> [<a href="https://arxiv.org/pdf/2411.01805">pdf</a>, <a href="https://arxiv.org/format/2411.01805">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=You%2C+F">Fuming You</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+M">Minghui Fang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Li Tang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+R">Rongjie Huang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yongqi Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhou Zhao</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="2411.01805v1-abstract-short" style="display: inline;"> Motion-to-music and music-to-motion have been studied separately, each attracting substantial research interest within their respective domains. The interaction between human motion and music is a reflection of advanced human intelligence, and establishing a unified relationship between them is particularly important. However, to date, there has been no work that considers them jointly to explore… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01805v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01805v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01805v1-abstract-full" style="display: none;"> Motion-to-music and music-to-motion have been studied separately, each attracting substantial research interest within their respective domains. The interaction between human motion and music is a reflection of advanced human intelligence, and establishing a unified relationship between them is particularly important. However, to date, there has been no work that considers them jointly to explore the modality alignment within. To bridge this gap, we propose a novel framework, termed MoMu-Diffusion, for long-term and synchronous motion-music generation. Firstly, to mitigate the huge computational costs raised by long sequences, we propose a novel Bidirectional Contrastive Rhythmic Variational Auto-Encoder (BiCoR-VAE) that extracts the modality-aligned latent representations for both motion and music inputs. Subsequently, leveraging the aligned latent spaces, we introduce a multi-modal Transformer-based diffusion model and a cross-guidance sampling strategy to enable various generation tasks, including cross-modal, multi-modal, and variable-length generation. Extensive experiments demonstrate that MoMu-Diffusion surpasses recent state-of-the-art methods both qualitatively and quantitatively, and can synthesize realistic, diverse, long-term, and beat-matched music or motion sequences. The generated samples and codes are available at https://momu-diffusion.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01805v1-abstract-full').style.display = 'none'; document.getElementById('2411.01805v1-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">NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01545">arXiv:2411.01545</a> <span> [<a href="https://arxiv.org/pdf/2411.01545">pdf</a>, <a href="https://arxiv.org/format/2411.01545">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3664647">10.1145/3664647 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+Q">Qihe Pan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhen Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zicheng Wang</a>, <a href="/search/cs?searchtype=author&query=Long%2C+S">Sifan Long</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yiming Wu</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+W">Wei Ji</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+H">Haoran Liang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+R">Ronghua 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="2411.01545v1-abstract-short" style="display: inline;"> A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in producing high-quality images, their application to small object generation has been limited due to difficulties in aligning cross-modal attention maps between t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01545v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01545v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01545v1-abstract-full" style="display: none;"> A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in producing high-quality images, their application to small object generation has been limited due to difficulties in aligning cross-modal attention maps between text and these objects. Our approach offers a training-free method that significantly mitigates this alignment issue with local and global attention guidance , enhancing the model's ability to accurately render small objects in accordance with textual descriptions. We detail the methodology in our approach, emphasizing its divergence from traditional generation techniques and highlighting its advantages. What's more important is that we also provide~\textit{SOEBench} (Small Object Editing), a standardized benchmark for quantitatively evaluating text-based small object generation collected from \textit{MSCOCO} and \textit{OpenImage}. Preliminary results demonstrate the effectiveness of our method, showing marked improvements in the fidelity and accuracy of small object generation compared to existing models. This advancement not only contributes to the field of AI and computer vision but also opens up new possibilities for applications in various industries where precise image generation is critical. We will release our dataset on our project page: \href{https://soebench.github.io/}{https://soebench.github.io/}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01545v1-abstract-full').style.display = 'none'; document.getElementById('2411.01545v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 8 figures, Accepted by ACMMM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01409">arXiv:2411.01409</a> <span> [<a href="https://arxiv.org/pdf/2411.01409">pdf</a>, <a href="https://arxiv.org/format/2411.01409">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> <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"> Classifier-guided Gradient Modulation for Enhanced Multimodal Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Zirun Guo</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+T">Tao Jin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jingyuan Chen</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhou Zhao</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="2411.01409v1-abstract-short" style="display: inline;"> Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other modalities. Existing methods to balance the training process always have some limitations on the loss functions, optimizers and the number of modalities and only consi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01409v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01409v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01409v1-abstract-full" style="display: none;"> Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other modalities. Existing methods to balance the training process always have some limitations on the loss functions, optimizers and the number of modalities and only consider modulating the magnitude of the gradients while ignoring the directions of the gradients. To solve these problems, in this paper, we present a novel method to balance multimodal learning with Classifier-Guided Gradient Modulation (CGGM), considering both the magnitude and directions of the gradients. We conduct extensive experiments on four multimodal datasets: UPMC-Food 101, CMU-MOSI, IEMOCAP and BraTS 2021, covering classification, regression and segmentation tasks. The results show that CGGM outperforms all the baselines and other state-of-the-art methods consistently, demonstrating its effectiveness and versatility. Our code is available at https://github.com/zrguo/CGGM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01409v1-abstract-full').style.display = 'none'; document.getElementById('2411.01409v1-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">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01376">arXiv:2411.01376</a> <span> [<a href="https://arxiv.org/pdf/2411.01376">pdf</a>, <a href="https://arxiv.org/format/2411.01376">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Multi-Channel Hypergraph Contrastive Learning for Matrix Completion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/cs?searchtype=author&query=Shui%2C+C">Changsheng Shui</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yanwei Yu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+C">Chao Huang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhongying Zhao</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Junyu Dong</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="2411.01376v1-abstract-short" style="display: inline;"> Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, which is also a significant problem in recommender systems. Recently, graph neural networks (GNNs) have been widely used in matrix completion, which captures users' preferences over items by formulating a rating matrix as… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01376v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01376v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01376v1-abstract-full" style="display: none;"> Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, which is also a significant problem in recommender systems. Recently, graph neural networks (GNNs) have been widely used in matrix completion, which captures users' preferences over items by formulating a rating matrix as a bipartite graph. However, existing methods are susceptible due to data sparsity and long-tail distribution in real-world scenarios. Moreover, the messaging mechanism of GNNs makes it difficult to capture high-order correlations and constraints between nodes, which are essentially useful in recommendation tasks. To tackle these challenges, we propose a Multi-Channel Hypergraph Contrastive Learning framework for matrix completion, named MHCL. Specifically, MHCL adaptively learns hypergraph structures to capture high-order correlations between nodes and jointly captures local and global collaborative relationships through attention-based cross-view aggregation. Additionally, to consider the magnitude and order information of ratings, we treat different rating subgraphs as different channels, encourage alignment between adjacent ratings, and further achieve the mutual enhancement between different ratings through multi-channel cross-rating contrastive learning. Extensive experiments on five public datasets demonstrate that the proposed method significantly outperforms the current state-of-the-art approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01376v1-abstract-full').style.display = 'none'; document.getElementById('2411.01376v1-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">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/2410.23736">arXiv:2410.23736</a> <span> [<a href="https://arxiv.org/pdf/2410.23736">pdf</a>, <a href="https://arxiv.org/format/2410.23736">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> MoTaDual: Modality-Task Dual Alignment for Enhanced Zero-shot Composed Image Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+H">Haiwen Li</a>, <a href="/search/cs?searchtype=author&query=Su%2C+F">Fei Su</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhicheng Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23736v1-abstract-short" style="display: inline;"> Composed Image Retrieval (CIR) is a challenging vision-language task, utilizing bi-modal (image+text) queries to retrieve target images. Despite the impressive performance of supervised CIR, the dependence on costly, manually-labeled triplets limits its scalability and zero-shot capability. To address this issue, zero-shot composed image retrieval (ZS-CIR) is presented along with projection-based… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23736v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23736v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23736v1-abstract-full" style="display: none;"> Composed Image Retrieval (CIR) is a challenging vision-language task, utilizing bi-modal (image+text) queries to retrieve target images. Despite the impressive performance of supervised CIR, the dependence on costly, manually-labeled triplets limits its scalability and zero-shot capability. To address this issue, zero-shot composed image retrieval (ZS-CIR) is presented along with projection-based approaches. However, such methods face two major problems, i.e., task discrepancy between pre-training (image $\leftrightarrow$ text) and inference (image+text $\rightarrow$ image), and modality discrepancy. The latter pertains to approaches based on text-only projection training due to the necessity of feature extraction from the reference image during inference. In this paper, we propose a two-stage framework to tackle both discrepancies. First, to ensure efficiency and scalability, a textual inversion network is pre-trained on large-scale caption datasets. Subsequently, we put forward Modality-Task Dual Alignment (MoTaDual) as the second stage, where large-language models (LLMs) generate triplet data for fine-tuning, and additionally, prompt learning is introduced in a multi-modal context to effectively alleviate both modality and task discrepancies. The experimental results show that our MoTaDual achieves the state-of-the-art performance across four widely used ZS-CIR benchmarks, while maintaining low training time and computational cost. The code will be released soon. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23736v1-abstract-full').style.display = 'none'; document.getElementById('2410.23736v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23090">arXiv:2410.23090</a> <span> [<a href="https://arxiv.org/pdf/2410.23090">pdf</a>, <a href="https://arxiv.org/format/2410.23090">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> </div> </div> <p class="title is-5 mathjax"> CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yiruo Cheng</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+K">Kelong Mao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziliang Zhao</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+G">Guanting Dong</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+H">Hongjin Qian</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yongkang Wu</a>, <a href="/search/cs?searchtype=author&query=Sakai%2C+T">Tetsuya Sakai</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23090v1-abstract-short" style="display: inline;"> Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23090v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23090v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23090v1-abstract-full" style="display: none;"> Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia and tackles key challenges such as open-domain coverage, knowledge intensity, free-form responses, and topic shifts. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling. We propose a unified framework to standardize various conversational RAG methods and conduct a comprehensive evaluation of these methods on CORAL, demonstrating substantial opportunities for improving existing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23090v1-abstract-full').style.display = 'none'; document.getElementById('2410.23090v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22722">arXiv:2410.22722</a> <span> [<a href="https://arxiv.org/pdf/2410.22722">pdf</a>, <a href="https://arxiv.org/ps/2410.22722">ps</a>, <a href="https://arxiv.org/format/2410.22722">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="Computational Geometry">cs.CG</span> </div> </div> <p class="title is-5 mathjax"> Enhancing binary classification: A new stacking method via leveraging computational geometry </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+W">Wei Wu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Liang Tang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhongjie Zhao</a>, <a href="/search/cs?searchtype=author&query=Teo%2C+C">Chung-Piaw Teo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.22722v1-abstract-short" style="display: inline;"> Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such as logistic regression, as the meta-model. This paper introduces a novel approach that integrates computational geometry techniques, specifically solving the m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22722v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22722v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22722v1-abstract-full" style="display: none;"> Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such as logistic regression, as the meta-model. This paper introduces a novel approach that integrates computational geometry techniques, specifically solving the maximum weighted rectangle problem, to develop a new meta-model for binary classification. Our method is evaluated on multiple open datasets, with statistical analysis showing its stability and demonstrating improvements in accuracy compared to current state-of-the-art stacking methods with out-of-fold predictions. This new stacking method also boasts two significant advantages: enhanced interpretability and the elimination of hyperparameter tuning for the meta-model, thus increasing its practicality. These merits make our method highly applicable not only in stacking ensemble learning but also in various real-world applications, such as hospital health evaluation scoring and bank credit scoring systems, offering a fresh evaluation perspective. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22722v1-abstract-full').style.display = 'none'; document.getElementById('2410.22722v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T05; 68U05 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.3.6; G.2.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22691">arXiv:2410.22691</a> <span> [<a href="https://arxiv.org/pdf/2410.22691">pdf</a>, <a href="https://arxiv.org/format/2410.22691">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div 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/LRA.2024.3487516">10.1109/LRA.2024.3487516 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MiniTac: An Ultra-Compact 8 mm Vision-Based Tactile Sensor for Enhanced Palpation in Robot-Assisted Minimally Invasive Surgery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wanlin Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zihang Zhao</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+L">Leiyao Cui</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hangxin Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Li-An Li</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yixin Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.22691v1-abstract-short" style="display: inline;"> Robot-assisted minimally invasive surgery (RAMIS) provides substantial benefits over traditional open and laparoscopic methods. However, a significant limitation of RAMIS is the surgeon's inability to palpate tissues, a crucial technique for examining tissue properties and detecting abnormalities, restricting the widespread adoption of RAMIS. To overcome this obstacle, we introduce MiniTac, a nove… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22691v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22691v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22691v1-abstract-full" style="display: none;"> Robot-assisted minimally invasive surgery (RAMIS) provides substantial benefits over traditional open and laparoscopic methods. However, a significant limitation of RAMIS is the surgeon's inability to palpate tissues, a crucial technique for examining tissue properties and detecting abnormalities, restricting the widespread adoption of RAMIS. To overcome this obstacle, we introduce MiniTac, a novel vision-based tactile sensor with an ultra-compact cross-sectional diameter of 8 mm, designed for seamless integration into mainstream RAMIS devices, particularly the Da Vinci surgical systems. MiniTac features a novel mechanoresponsive photonic elastomer membrane that changes color distribution under varying contact pressures. This color change is captured by an embedded miniature camera, allowing MiniTac to detect tumors both on the tissue surface and in deeper layers typically obscured from endoscopic view. MiniTac's efficacy has been rigorously tested on both phantoms and ex-vivo tissues. By leveraging advanced mechanoresponsive photonic materials, MiniTac represents a significant advancement in integrating tactile sensing into RAMIS, potentially expanding its applicability to a wider array of clinical scenarios that currently rely on traditional surgical approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22691v1-abstract-full').style.display = 'none'; document.getElementById('2410.22691v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted for publication in the IEEE Robotics and Automation Letters (RA-L)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21269">arXiv:2410.21269</a> <span> [<a href="https://arxiv.org/pdf/2410.21269">pdf</a>, <a href="https://arxiv.org/format/2410.21269">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xize Cheng</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Siqi Zheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zehan Wang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+M">Minghui Fang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Ziang Zhang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+R">Rongjie Huang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Z">Ziyang Ma</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+S">Shengpeng Ji</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+J">Jialong Zuo</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+T">Tao Jin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhou Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21269v1-abstract-short" style="display: inline;"> The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtrac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21269v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21269v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21269v1-abstract-full" style="display: none;"> The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtracks based on omni-modal queries, encompassing both single-modal and multi-modal composed queries. Specifically, we introduce the Query-Mixup strategy, which blends query features from different modalities during training. This enables OmniSep to optimize multiple modalities concurrently, effectively bringing all modalities under a unified framework for sound separation. We further enhance this flexibility by allowing queries to influence sound separation positively or negatively, facilitating the retention or removal of specific sounds as desired. Finally, OmniSep employs a retrieval-augmented approach known as Query-Aug, which enables open-vocabulary sound separation. Experimental evaluations on MUSIC, VGGSOUND-CLEAN+, and MUSIC-CLEAN+ datasets demonstrate effectiveness of OmniSep, achieving state-of-the-art performance in text-, image-, and audio-queried sound separation tasks. For samples and further information, please visit the demo page at \url{https://omnisep.github.io/}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21269v1-abstract-full').style.display = 'none'; document.getElementById('2410.21269v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Working in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21160">arXiv:2410.21160</a> <span> [<a href="https://arxiv.org/pdf/2410.21160">pdf</a>, <a href="https://arxiv.org/format/2410.21160">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhihao Zhao</a>, <a href="/search/cs?searchtype=author&query=Faghihroohi%2C+S">Shahrooz Faghihroohi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yinzheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junjie Yang</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+S">Shipeng Zhong</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+K">Kai Huang</a>, <a href="/search/cs?searchtype=author&query=Navab%2C+N">Nassir Navab</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Boyang Li</a>, <a href="/search/cs?searchtype=author&query=Nasseri%2C+M+A">M. Ali Nasseri</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21160v1-abstract-short" style="display: inline;"> Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various eye diseases. Contemporary deep learning-based vascular segmentation models rival human accuracy but still face substantial challenges in accurately segmenting minuscule blood vessels in neural network applications. Due to the necessity of multiple downsampl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21160v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21160v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21160v1-abstract-full" style="display: none;"> Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various eye diseases. Contemporary deep learning-based vascular segmentation models rival human accuracy but still face substantial challenges in accurately segmenting minuscule blood vessels in neural network applications. Due to the necessity of multiple downsampling operations in the CNN models, fine details from high-resolution images are inevitably lost. The objective of this study is to design a structure to capture the delicate and small blood vessels. Methods: To address these issues, we propose a novel network (KaLDeX) for vascular segmentation leveraging a Kalman filter based linear deformable cross attention (LDCA) module, integrated within a UNet++ framework. Our approach is based on two key components: Kalman filter (KF) based linear deformable convolution (LD) and cross-attention (CA) modules. The LD module is designed to adaptively adjust the focus on thin vessels that might be overlooked in standard convolution. The CA module improves the global understanding of vascular structures by aggregating the detailed features from the LD module with the high level features from the UNet++ architecture. Finally, we adopt a topological loss function based on persistent homology to constrain the topological continuity of the segmentation. Results: The proposed method is evaluated on retinal fundus image datasets (DRIVE, CHASE_BD1, and STARE) as well as the 3mm and 6mm of the OCTA-500 dataset, achieving an average accuracy (ACC) of 97.25%, 97.77%, 97.85%, 98.89%, and 98.21%, respectively. Conclusions: Empirical evidence shows that our method outperforms the current best models on different vessel segmentation datasets. Our source code is available at: https://github.com/AIEyeSystem/KalDeX. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21160v1-abstract-full').style.display = 'none'; document.getElementById('2410.21160v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21130">arXiv:2410.21130</a> <span> [<a href="https://arxiv.org/pdf/2410.21130">pdf</a>, <a href="https://arxiv.org/format/2410.21130">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"> Extrapolating Prospective Glaucoma Fundus Images through Diffusion Model in Irregular Longitudinal Sequences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhihao Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junjie Yang</a>, <a href="/search/cs?searchtype=author&query=Faghihroohi%2C+S">Shahrooz Faghihroohi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yinzheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Zapp%2C+D">Daniel Zapp</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+K">Kai Huang</a>, <a href="/search/cs?searchtype=author&query=Navab%2C+N">Nassir Navab</a>, <a href="/search/cs?searchtype=author&query=Nasseri%2C+M+A">M. Ali Nasseri</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21130v2-abstract-short" style="display: inline;"> The utilization of longitudinal datasets for glaucoma progression prediction offers a compelling approach to support early therapeutic interventions. Predominant methodologies in this domain have primarily focused on the direct prediction of glaucoma stage labels from longitudinal datasets. However, such methods may not adequately encapsulate the nuanced developmental trajectory of the disease. To… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21130v2-abstract-full').style.display = 'inline'; document.getElementById('2410.21130v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21130v2-abstract-full" style="display: none;"> The utilization of longitudinal datasets for glaucoma progression prediction offers a compelling approach to support early therapeutic interventions. Predominant methodologies in this domain have primarily focused on the direct prediction of glaucoma stage labels from longitudinal datasets. However, such methods may not adequately encapsulate the nuanced developmental trajectory of the disease. To enhance the diagnostic acumen of medical practitioners, we propose a novel diffusion-based model to predict prospective images by extrapolating from existing longitudinal fundus images of patients. The methodology delineated in this study distinctively leverages sequences of images as inputs. Subsequently, a time-aligned mask is employed to select a specific year for image generation. During the training phase, the time-aligned mask resolves the issue of irregular temporal intervals in longitudinal image sequence sampling. Additionally, we utilize a strategy of randomly masking a frame in the sequence to establish the ground truth. This methodology aids the network in continuously acquiring knowledge regarding the internal relationships among the sequences throughout the learning phase. Moreover, the introduction of textual labels is instrumental in categorizing images generated within the sequence. The empirical findings from the conducted experiments indicate that our proposed model not only effectively generates longitudinal data but also significantly improves the precision of downstream classification tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21130v2-abstract-full').style.display = 'none'; document.getElementById('2410.21130v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at BIBM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20466">arXiv:2410.20466</a> <span> [<a href="https://arxiv.org/pdf/2410.20466">pdf</a>, <a href="https://arxiv.org/format/2410.20466">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhicheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Juanjuan Gu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chenglong Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chun Wang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhongling Huang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jin Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.20466v1-abstract-short" style="display: inline;"> Optics-guided Thermal UAV image Super-Resolution (OTUAV-SR) has attracted significant research interest due to its potential applications in security inspection, agricultural measurement, and object detection. Existing methods often employ single guidance model to generate the guidance features from optical images to assist thermal UAV images super-resolution. However, single guidance models make… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20466v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20466v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20466v1-abstract-full" style="display: none;"> Optics-guided Thermal UAV image Super-Resolution (OTUAV-SR) has attracted significant research interest due to its potential applications in security inspection, agricultural measurement, and object detection. Existing methods often employ single guidance model to generate the guidance features from optical images to assist thermal UAV images super-resolution. However, single guidance models make it difficult to generate effective guidance features under favorable and adverse conditions in UAV scenarios, thus limiting the performance of OTUAV-SR. To address this issue, we propose a novel Guidance Disentanglement network (GDNet), which disentangles the optical image representation according to typical UAV scenario attributes to form guidance features under both favorable and adverse conditions, for robust OTUAV-SR. Moreover, we design an attribute-aware fusion module to combine all attribute-based optical guidance features, which could form a more discriminative representation and fit the attribute-agnostic guidance process. To facilitate OTUAV-SR research in complex UAV scenarios, we introduce VGTSR2.0, a large-scale benchmark dataset containing 3,500 aligned optical-thermal image pairs captured under diverse conditions and scenes. Extensive experiments on VGTSR2.0 demonstrate that GDNet significantly improves OTUAV-SR performance over state-of-the-art methods, especially in the challenging low-light and foggy environments commonly encountered in UAV scenarios. The dataset and code will be publicly available at https://github.com/Jocelyney/GDNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20466v1-abstract-full').style.display = 'none'; document.getElementById('2410.20466v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 19 figures, 8 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20008">arXiv:2410.20008</a> <span> [<a href="https://arxiv.org/pdf/2410.20008">pdf</a>, <a href="https://arxiv.org/format/2410.20008">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"> Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zheng Zhao</a>, <a href="/search/cs?searchtype=author&query=Ziser%2C+Y">Yftah Ziser</a>, <a href="/search/cs?searchtype=author&query=Cohen%2C+S+B">Shay B. Cohen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.20008v1-abstract-short" style="display: inline;"> Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models retain task-specific knowledge remains largely unexplored. This study investigates the task-specific information encoded in pre-trained LLMs and the effects of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20008v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20008v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20008v1-abstract-full" style="display: none;"> Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models retain task-specific knowledge remains largely unexplored. This study investigates the task-specific information encoded in pre-trained LLMs and the effects of instruction tuning on their representations across a diverse set of over 60 NLP tasks. We use a set of matrix analysis tools to examine the differences between the way pre-trained and instruction-tuned LLMs store task-specific information. Our findings reveal that while some tasks are already encoded within the pre-trained LLMs, others greatly benefit from instruction tuning. Additionally, we pinpointed the layers in which the model transitions from high-level general representations to more task-oriented representations. This finding extends our understanding of the governing mechanisms of LLMs and facilitates future research in the fields of parameter-efficient transfer learning and multi-task learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20008v1-abstract-full').style.display = 'none'; document.getElementById('2410.20008v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to EMNLP 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19848">arXiv:2410.19848</a> <span> [<a href="https://arxiv.org/pdf/2410.19848">pdf</a>, <a href="https://arxiv.org/format/2410.19848">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Benchmarking Large Language Models for Image Classification of Marine Mammals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qi%2C+Y">Yijiashun Qi</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+S">Shuzhang Cai</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zunduo Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaming Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yanbin Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhiqiang Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19848v1-abstract-short" style="display: inline;"> As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on mari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19848v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19848v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19848v1-abstract-full" style="display: none;"> As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on marine mammals, which are indispensable for ecological equilibrium. In this work, we build a benchmark dataset with 1,423 images of 65 kinds of marine mammals, where each animal is uniquely classified into different levels of class, ranging from species-level to medium-level to group-level. Moreover, we evaluate several approaches for classifying these marine mammals: (1) machine learning (ML) algorithms using embeddings provided by neural networks, (2) influential pre-trained neural networks, (3) zero-shot models: CLIP and LLMs, and (4) a novel LLM-based multi-agent system (MAS). The results demonstrate the strengths of traditional models and LLMs in different aspects, and the MAS can further improve the classification performance. The dataset is available on GitHub: https://github.com/yeyimilk/LLM-Vision-Marine-Animals.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19848v1-abstract-full').style.display = 'none'; document.getElementById('2410.19848v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICKG 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19245">arXiv:2410.19245</a> <span> [<a href="https://arxiv.org/pdf/2410.19245">pdf</a>, <a href="https://arxiv.org/format/2410.19245">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</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"> VisionCoder: Empowering Multi-Agent Auto-Programming for Image Processing with Hybrid LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zixiao Zhao</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jing Sun</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Z">Zhiyuan Wei</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+C">Cheng-Hao Cai</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+Z">Zhe Hou</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J+S">Jin Song Dong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19245v1-abstract-short" style="display: inline;"> In the field of automated programming, large language models (LLMs) have demonstrated foundational generative capabilities when given detailed task descriptions. However, their current functionalities are primarily limited to function-level development, restricting their effectiveness in complex project environments and specific application scenarios, such as complicated image-processing tasks. Th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19245v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19245v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19245v1-abstract-full" style="display: none;"> In the field of automated programming, large language models (LLMs) have demonstrated foundational generative capabilities when given detailed task descriptions. However, their current functionalities are primarily limited to function-level development, restricting their effectiveness in complex project environments and specific application scenarios, such as complicated image-processing tasks. This paper presents a multi-agent framework that utilises a hybrid set of LLMs, including GPT-4o and locally deployed open-source models, which collaboratively complete auto-programming tasks. Each agent plays a distinct role in the software development cycle, collectively forming a virtual organisation that works together to produce software products. By establishing a tree-structured thought distribution and development mechanism across project, module, and function levels, this framework offers a cost-effective and efficient solution for code generation. We evaluated our approach using benchmark datasets, and the experimental results demonstrate that VisionCoder significantly outperforms existing methods in image processing auto-programming tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19245v1-abstract-full').style.display = 'none'; document.getElementById('2410.19245v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19195">arXiv:2410.19195</a> <span> [<a href="https://arxiv.org/pdf/2410.19195">pdf</a>, <a href="https://arxiv.org/format/2410.19195">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"> Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yue Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhixue Zhao</a>, <a href="/search/cs?searchtype=author&query=Scarton%2C+C">Carolina Scarton</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19195v1-abstract-short" style="display: inline;"> In-context learning (ICL) performance is known to be sensitive to the prompt design, yet the impact of class label options in zero-shot classification has been largely overlooked. This study presents the first comprehensive empirical study investigating how label option (e.g., lexical choice, order, and elaboration) influences zero-shot ICL classification performance. Our findings reveal that lexi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19195v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19195v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19195v1-abstract-full" style="display: none;"> In-context learning (ICL) performance is known to be sensitive to the prompt design, yet the impact of class label options in zero-shot classification has been largely overlooked. This study presents the first comprehensive empirical study investigating how label option (e.g., lexical choice, order, and elaboration) influences zero-shot ICL classification performance. Our findings reveal that lexical choices for label names (e.g., agree vs.support in stance classification) play an important role, with effects also linked to label orders. An analysis of the model internal states further shows that optimal label names tend to activate fewer outlier neurons in the feed forward network. Based on this observation, we propose Label set Optimization via Activation Distribution kurtosiS (LOADS), a post-hoc approach requiring no gradient propagation. LOADS not only demonstrates effectiveness with only 100 unlabelled samples across different model types and sizes, but also shows cross-lingual transferability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19195v1-abstract-full').style.display = 'none'; document.getElementById('2410.19195v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18742">arXiv:2410.18742</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Continuous Dynamic Modeling via Neural ODEs for Popularity Trajectory Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Songbo Yang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziwei Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zihang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haotian Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tong Xu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+M">Mengxiao Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18742v2-abstract-short" style="display: inline;"> Popularity prediction for information cascades has significant applications across various domains, including opinion monitoring and advertising recommendations. While most existing methods consider this as a discrete problem, popularity actually evolves continuously, exhibiting rich dynamic properties such as change rates and growth patterns. In this paper, we argue that popularity trajectory pre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18742v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18742v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18742v2-abstract-full" style="display: none;"> Popularity prediction for information cascades has significant applications across various domains, including opinion monitoring and advertising recommendations. While most existing methods consider this as a discrete problem, popularity actually evolves continuously, exhibiting rich dynamic properties such as change rates and growth patterns. In this paper, we argue that popularity trajectory prediction is more practical, as it aims to forecast the entire trajectory of how popularity unfolds over arbitrary future time. This approach offers insights into both instantaneous popularity and the underlying dynamic properties. However, traditional methods for popularity trajectory prediction primarily rely on specific diffusion mechanism assumptions, which may not align well with real-world dynamics and compromise their performance. To address these limitations, we propose NODEPT, a novel approach based on neural ordinary differential equations (ODEs) for popularity trajectory prediction. NODEPT models the continuous dynamics of the underlying diffusion system using neural ODEs. We first employ an encoder to initialize the latent state representations of information cascades, consisting of two representation learning modules that capture the co-evolution structural characteristics and temporal patterns of cascades from different perspectives. More importantly, we then introduce an ODE-based generative module that learns the dynamics of the diffusion system in the latent space. Finally, a decoder transforms the latent state into the prediction of the future popularity trajectory. Our experimental results on three real-world datasets demonstrate the superiority and rationality of the proposed NODEPT method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18742v2-abstract-full').style.display = 'none'; document.getElementById('2410.18742v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The time complexity analysis in section 4.4 contains error; we overlooked the impact of the memory module</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18715">arXiv:2410.18715</a> <span> [<a href="https://arxiv.org/pdf/2410.18715">pdf</a>, <a href="https://arxiv.org/format/2410.18715">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"> ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zijia Zhao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+L">Longteng Guo</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+T">Tongtian Yue</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+E">Erdong Hu</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+S">Shuai Shao</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+Z">Zehuan Yuan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hua Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jing Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18715v1-abstract-short" style="display: inline;"> In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18715v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18715v1-abstract-full" style="display: none;"> In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval system to find the accurate image from database. Simultaneously, we propose a generative retrieval model named ChatSearcher, which is trained end-to-end to accept/produce interleaved image-text inputs/outputs. ChatSearcher exhibits strong capability in reasoning with multimodal context and can leverage world knowledge to yield visual retrieval results. It demonstrates superior performance on the ChatSearch dataset and also achieves competitive results on other image retrieval tasks and visual conversation tasks. We anticipate that this work will inspire further research on interactive multimodal retrieval systems. Our dataset will be available at https://github.com/joez17/ChatSearch. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18715v1-abstract-full').style.display = 'none'; document.getElementById('2410.18715v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18634">arXiv:2410.18634</a> <span> [<a href="https://arxiv.org/pdf/2410.18634">pdf</a>, <a href="https://arxiv.org/format/2410.18634">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Little Giants: Synthesizing High-Quality Embedding Data at Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haonan Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+N">Nan Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yutao Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Ziliang Zhao</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+F">Furu Wei</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18634v2-abstract-short" style="display: inline;"> Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples, significantly reducing the cost of human annotation. However, most current approaches rely heavily on proprietary models like GPT-4, which are expensive and inefficient… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18634v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18634v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18634v2-abstract-full" style="display: none;"> Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples, significantly reducing the cost of human annotation. However, most current approaches rely heavily on proprietary models like GPT-4, which are expensive and inefficient for generating large-scale embedding data. In this paper, we introduce SPEED, a framework that aligns open-source small models (8B) to efficiently generate large-scale synthetic embedding data. Through supervised fine-tuning, preference optimization, and self-improvement, SPEED enables small open-source models to produce high-quality data. Remarkably, SPEED uses only less than 1/10 of the GPT API calls, outperforming the state-of-the-art embedding model E5_mistral when both are trained solely on their synthetic data. Using this efficient generator, we conduct a comprehensive study on how various factors within the alignment pipeline impact data quality and reveal the scaling law for synthetic embedding data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18634v2-abstract-full').style.display = 'none'; document.getElementById('2410.18634v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16502">arXiv:2410.16502</a> <span> [<a href="https://arxiv.org/pdf/2410.16502">pdf</a>, <a href="https://arxiv.org/format/2410.16502">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"> Rulebreakers Challenge: Revealing a Blind Spot in Large Language Models' Reasoning with Formal Logic </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chan%2C+J">Jason Chan</a>, <a href="/search/cs?searchtype=author&query=Gaizauskas%2C+R">Robert Gaizauskas</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhixue Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.16502v1-abstract-short" style="display: inline;"> Formal logic has long been applied to natural language reasoning, but this approach can sometimes lead to conclusions that, while logically entailed, are factually inconsistent with the premises or are not typically inferred by humans. This study introduces the concept of "rulebreakers", which refers to instances where logical entailment diverges from factually acceptable inference. We present RUL… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16502v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16502v1-abstract-full" style="display: none;"> Formal logic has long been applied to natural language reasoning, but this approach can sometimes lead to conclusions that, while logically entailed, are factually inconsistent with the premises or are not typically inferred by humans. This study introduces the concept of "rulebreakers", which refers to instances where logical entailment diverges from factually acceptable inference. We present RULEBREAKERS, a novel dataset for evaluating Large Language Models' (LLMs) ability to distinguish between rulebreakers and non-rulebreakers. Focusing on modus tollens and disjunctive syllogism, we assess six state-of-the-art LLMs using RULEBREAKERS, measuring their performance in terms of token-level exact accuracy and model confidence. Our findings reveal that while most models perform poorly to moderately in recognizing rulebreakers, they demonstrate a latent ability to distinguish rulebreakers when assessed by their confidence levels. Further analysis suggests that the failure to recognize rulebreakers is potentially associated with the models' world knowledge and their attention distribution patterns. This research highlights the limitation of LLMs' reasoning capabilities, and contributes to the ongoing discussion on reasoning in LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16502v1-abstract-full').style.display = 'none'; document.getElementById('2410.16502v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16166">arXiv:2410.16166</a> <span> [<a href="https://arxiv.org/pdf/2410.16166">pdf</a>, <a href="https://arxiv.org/format/2410.16166">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+H">Han Huang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yuqi Huo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zijia Zhao</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Haoyu Lu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shu Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bingning Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weipeng Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.16166v1-abstract-short" style="display: inline;"> Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16166v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16166v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16166v1-abstract-full" style="display: none;"> Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically assesses and enhances the quality of image-text pairs. AITQE employs a text rewriting mechanism for low-quality pairs and incorporates a negative sample learning strategy to improve evaluative capabilities by integrating deliberately selected low-quality samples during training. Unlike prior approaches that significantly alter text distributions, our method minimally adjusts text to preserve data volume while enhancing quality. Experimental results demonstrate that AITQE surpasses existing methods on various benchmark, effectively leveraging raw data and scaling efficiently with increasing data volumes. We hope our work will inspire future works. The code and model are available at: https://github.com/hanhuang22/AITQE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16166v1-abstract-full').style.display = 'none'; document.getElementById('2410.16166v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> </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=Zhao%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhao%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository