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 1,432 results for author: <span class="mathjax">Zhang, B</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Zhang%2C+B">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Zhang, B"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Zhang%2C+B&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Zhang, B"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&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/2411.12962">arXiv:2411.12962</a> <span> [<a href="https://arxiv.org/pdf/2411.12962">pdf</a>, <a href="https://arxiv.org/format/2411.12962">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Bring the Heat: Rapid Trajectory Optimization with Pseudospectral Techniques and the Affine Geometric Heat Flow Equation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Adu%2C+C+E">Challen Enninful Adu</a>, <a href="/search/cs?searchtype=author&query=Chuquiure%2C+C+E+R">C茅sar E. Ramos Chuquiure</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bohao Zhang</a>, <a href="/search/cs?searchtype=author&query=Vasudevan%2C+R">Ram Vasudevan</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="2411.12962v1-abstract-short" style="display: inline;"> Generating optimal trajectories for high-dimensional robotic systems in a time-efficient manner while adhering to constraints is a challenging task. To address this challenge, this paper introduces PHLAME, which applies pseudospectral collocation and spatial vector algebra to efficiently solve the Affine Geometric Heat Flow (AGHF) Partial Differential Equation (PDE) for trajectory optimization. Un… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12962v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12962v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12962v1-abstract-full" style="display: none;"> Generating optimal trajectories for high-dimensional robotic systems in a time-efficient manner while adhering to constraints is a challenging task. To address this challenge, this paper introduces PHLAME, which applies pseudospectral collocation and spatial vector algebra to efficiently solve the Affine Geometric Heat Flow (AGHF) Partial Differential Equation (PDE) for trajectory optimization. Unlike traditional PDE approaches like the Hamilton-Jacobi-Bellman (HJB) PDE, which solve for a function over the entire state space, computing a solution to the AGHF PDE scales more efficiently because its solution is defined over a two-dimensional domain, thereby avoiding the intractability of state-space scaling. To solve the AGHF one usually applies the Method of Lines (MOL), which works by discretizing one variable of the AGHF PDE, effectively converting the PDE into a system of ordinary differential equations (ODEs) that can be solved using standard time-integration methods. Though powerful, this method requires a fine discretization to generate accurate solutions and still requires evaluating the AGHF PDE which can be computationally expensive for high-dimensional systems. PHLAME overcomes this deficiency by using a pseudospectral method, which reduces the number of function evaluations required to yield a high accuracy solution thereby allowing it to scale efficiently to high-dimensional robotic systems. To further increase computational speed, this paper presents analytical expressions for the AGHF and its Jacobian, both of which can be computed efficiently using rigid body dynamics algorithms. The proposed method PHLAME is tested across various dynamical systems, with and without obstacles and compared to a number of state-of-the-art techniques. PHLAME generates trajectories for a 44-dimensional state-space system in $\sim3$ seconds, much faster than current state-of-the-art techniques. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12962v1-abstract-full').style.display = 'none'; document.getElementById('2411.12962v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, 8 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/2411.12951">arXiv:2411.12951</a> <span> [<a href="https://arxiv.org/pdf/2411.12951">pdf</a>, <a href="https://arxiv.org/format/2411.12951">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"> On the Consistency of Video Large Language Models in Temporal Comprehension </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jung%2C+M">Minjoon Jung</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Junbin Xiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Byoung-Tak Zhang</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+A">Angela Yao</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="2411.12951v1-abstract-short" style="display: inline;"> Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12951v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12951v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12951v1-abstract-full" style="display: none;"> Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations in video contents, language queries, and task settings, unveiling severe deficiencies in maintaining consistency. We further explore common prompting and instruction-tuning methods as potential solutions, but find that their improvements are often unstable. To that end, we propose event temporal verification tuning that explicitly accounts for consistency, and demonstrate significant improvements for both grounding and consistency. Our data and code will be available at https://github.com/minjoong507/Consistency-of-Video-LLM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12951v1-abstract-full').style.display = 'none'; document.getElementById('2411.12951v1-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/2411.12259">arXiv:2411.12259</a> <span> [<a href="https://arxiv.org/pdf/2411.12259">pdf</a>, <a href="https://arxiv.org/format/2411.12259">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"> Prototype Optimization with Neural ODE for Few-Shot Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baoquan Zhang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+S">Shanshan Feng</a>, <a href="/search/cs?searchtype=author&query=Shan%2C+B">Bingqi Shan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xutao Li</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yunming Ye</a>, <a href="/search/cs?searchtype=author&query=Ong%2C+Y">Yew-Soon Ong</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="2411.12259v1-abstract-short" style="display: inline;"> Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then performing class prediction via a cosine classifier with mean-based prototypes. Nevertheless, due to the data scarcity, the mean-based prototypes are usually biased. In this paper, we attempt t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12259v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12259v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12259v1-abstract-full" style="display: none;"> Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then performing class prediction via a cosine classifier with mean-based prototypes. Nevertheless, due to the data scarcity, the mean-based prototypes are usually biased. In this paper, we attempt to diminish the prototype bias by regarding it as a prototype optimization problem. To this end, we propose a novel prototype optimization framework to rectify prototypes, i.e., introducing a meta-optimizer to optimize prototypes. Although the existing meta-optimizers can also be adapted to our framework, they all overlook a crucial gradient bias issue, i.e., the mean-based gradient estimation is also biased on sparse data. To address this issue, in this paper, we regard the gradient and its flow as meta-knowledge and then propose a novel Neural Ordinary Differential Equation (ODE)-based meta-optimizer to optimize prototypes, called MetaNODE. Although MetaNODE has shown superior performance, it suffers from a huge computational burden. To further improve its computation efficiency, we conduct a detailed analysis on MetaNODE and then design an effective and efficient MetaNODE extension version (called E2MetaNODE). It consists of two novel modules: E2GradNet and E2Solver, which aim to estimate accurate gradient flows and solve optimal prototypes in an effective and efficient manner, respectively. Extensive experiments show that 1) our methods achieve superior performance over previous FSL methods and 2) our E2MetaNODE significantly improves computation efficiency meanwhile without performance degradation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12259v1-abstract-full').style.display = 'none'; document.getElementById('2411.12259v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">An extended version of metanode: prototype optimization as a neural ode for few-shot learning. arXiv admin note: text overlap with arXiv:2103.14341</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11360">arXiv:2411.11360</a> <span> [<a href="https://arxiv.org/pdf/2411.11360">pdf</a>, <a href="https://arxiv.org/format/2411.11360">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"> CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhiming Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mingze Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Sheng Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanjing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baochang 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="2411.11360v1-abstract-short" style="display: inline;"> Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categories, locations, and dynamics of changed objects (e.g., additions or disappearances). Many current methods attempt to leverage the long-sequence understanding and reasoning capabilities of multimodal large language models… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11360v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11360v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11360v1-abstract-full" style="display: none;"> Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categories, locations, and dynamics of changed objects (e.g., additions or disappearances). Many current methods attempt to leverage the long-sequence understanding and reasoning capabilities of multimodal large language models (MLLMs) for this task. However, without comprehensive data support, these approaches often alter the essential feature transmission pathways of MLLMs, disrupting the intrinsic knowledge within the models and limiting their potential in RSICC. In this paper, we propose a novel model, CCExpert, based on a new, advanced multimodal large model framework. Firstly, we design a difference-aware integration module to capture multi-scale differences between bi-temporal images and incorporate them into the original image context, thereby enhancing the signal-to-noise ratio of differential features. Secondly, we constructed a high-quality, diversified dataset called CC-Foundation, containing 200,000 image pairs and 1.2 million captions, to provide substantial data support for continue pretraining in this domain. Lastly, we employed a three-stage progressive training process to ensure the deep integration of the difference-aware integration module with the pretrained MLLM. CCExpert achieved a notable performance of $S^*_m=81.80$ on the LEVIR-CC benchmark, significantly surpassing previous state-of-the-art methods. The code and part of the dataset will soon be open-sourced at https://github.com/Meize0729/CCExpert. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11360v1-abstract-full').style.display = 'none'; document.getElementById('2411.11360v1-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/2411.10742">arXiv:2411.10742</a> <span> [<a href="https://arxiv.org/pdf/2411.10742">pdf</a>, <a href="https://arxiv.org/format/2411.10742">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"> It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+J">Jinkai Zheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinchen Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boyue Zhang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiyong Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wu Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongdong 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="2411.10742v1-abstract-short" style="display: inline;"> Existing studies for gait recognition primarily utilized sequences of either binary silhouette or human parsing to encode the shapes and dynamics of persons during walking. Silhouettes exhibit accurate segmentation quality and robustness to environmental variations, but their low information entropy may result in sub-optimal performance. In contrast, human parsing provides fine-grained part segmen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10742v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10742v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10742v1-abstract-full" style="display: none;"> Existing studies for gait recognition primarily utilized sequences of either binary silhouette or human parsing to encode the shapes and dynamics of persons during walking. Silhouettes exhibit accurate segmentation quality and robustness to environmental variations, but their low information entropy may result in sub-optimal performance. In contrast, human parsing provides fine-grained part segmentation with higher information entropy, but the segmentation quality may deteriorate due to the complex environments. To discover the advantages of silhouette and parsing and overcome their limitations, this paper proposes a novel cross-granularity alignment gait recognition method, named XGait, to unleash the power of gait representations of different granularity. To achieve this goal, the XGait first contains two branches of backbone encoders to map the silhouette sequences and the parsing sequences into two latent spaces, respectively. Moreover, to explore the complementary knowledge across the features of two representations, we design the Global Cross-granularity Module (GCM) and the Part Cross-granularity Module (PCM) after the two encoders. In particular, the GCM aims to enhance the quality of parsing features by leveraging global features from silhouettes, while the PCM aligns the dynamics of human parts between silhouette and parsing features using the high information entropy in parsing sequences. In addition, to effectively guide the alignment of two representations with different granularity at the part level, an elaborate-designed learnable division mechanism is proposed for the parsing features. Comprehensive experiments on two large-scale gait datasets not only show the superior performance of XGait with the Rank-1 accuracy of 80.5% on Gait3D and 88.3% CCPG but also reflect the robustness of the learned features even under challenging conditions like occlusions and cloth changes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10742v1-abstract-full').style.display = 'none'; document.getElementById('2411.10742v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 9 figures; Accepted by ACM MM 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/2411.09852">arXiv:2411.09852</a> <span> [<a href="https://arxiv.org/pdf/2411.09852">pdf</a>, <a href="https://arxiv.org/format/2411.09852">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="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"> InterFormer: Towards Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+Z">Zhichen Zeng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaolong Liu</a>, <a href="/search/cs?searchtype=author&query=Hang%2C+M">Mengyue Hang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoyi Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Q">Qinghai Zhou</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chaofei Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiqun Liu</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+Y">Yichen Ruan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Laming Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuxin Chen</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yujia Hao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiaqi Xu</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+J">Jade Nie</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xi Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Buyun Zhang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+W">Wei Wen</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Siyang Yuan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kai Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wen-Yen Chen</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yiping Han</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Huayu Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chunzhi Yang</a>, <a href="/search/cs?searchtype=author&query=Long%2C+B">Bo Long</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+H">Hanghang Tong</a> , et al. (1 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="2411.09852v1-abstract-short" style="display: inline;"> Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. How… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09852v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09852v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09852v1-abstract-full" style="display: none;"> Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09852v1-abstract-full').style.display = 'none'; document.getElementById('2411.09852v1-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">10 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09287">arXiv:2411.09287</a> <span> [<a href="https://arxiv.org/pdf/2411.09287">pdf</a>, <a href="https://arxiv.org/format/2411.09287">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"> The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+T">Tianpei Lu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bingsheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lichun Li</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+K">Kui Ren</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="2411.09287v1-abstract-short" style="display: inline;"> With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an innovative approach that allows for secure data analysis while safeguarding sensitive information. It enables organizations to extract valuable insights from da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09287v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09287v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09287v1-abstract-full" style="display: none;"> With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an innovative approach that allows for secure data analysis while safeguarding sensitive information. It enables organizations to extract valuable insights from data without compromising privacy. Secure multi-party computation (MPC) is a key tool in PPML, as it allows multiple parties to jointly compute functions without revealing their private inputs, making it essential in multi-server environments. We address the performance overhead of existing maliciously secure protocols, particularly in finite rings like $\mathbb{Z}_{2^\ell}$, by introducing an efficient protocol for secure linear function evaluation. We implement our maliciously secure MPC protocol on GPUs, significantly improving its efficiency and scalability. We extend the protocol to handle linear and non-linear layers, ensuring compatibility with a wide range of machine-learning models. Finally, we comprehensively evaluate machine learning models by integrating our protocol into the workflow, enabling secure and efficient inference across simple and complex models, such as convolutional neural networks (CNNs). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09287v1-abstract-full').style.display = 'none'; document.getElementById('2411.09287v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08374">arXiv:2411.08374</a> <span> [<a href="https://arxiv.org/pdf/2411.08374">pdf</a>, <a href="https://arxiv.org/format/2411.08374">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Federated Graph Learning with Graphless Clients </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+X">Xingbo Fu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Song Wang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yushun Dong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Binchi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jundong Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08374v1-abstract-short" style="display: inline;"> Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08374v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08374v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08374v1-abstract-full" style="display: none;"> Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments demonstrate the superiority of the proposed FedGLS over five baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08374v1-abstract-full').style.display = 'none'; document.getElementById('2411.08374v1-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">Accepted by Transactions on Machine Learning Research (TMLR)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07462">arXiv:2411.07462</a> <span> [<a href="https://arxiv.org/pdf/2411.07462">pdf</a>, <a href="https://arxiv.org/format/2411.07462">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"> MureObjectStitch: Multi-reference Image Composition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jiaxuan Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Li Niu</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="2411.07462v1-abstract-short" style="display: inline;"> Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which all… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07462v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07462v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07462v1-abstract-full" style="display: none;"> Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground object. The experiments on MureCOM dataset verify the effectiveness of our method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07462v1-abstract-full').style.display = 'none'; document.getElementById('2411.07462v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06665">arXiv:2411.06665</a> <span> [<a href="https://arxiv.org/pdf/2411.06665">pdf</a>, <a href="https://arxiv.org/format/2411.06665">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"> Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xinyang Huang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shanghang 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="2411.06665v1-abstract-short" style="display: inline;"> Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain strategies for target samples to adapt, ignoring the exploration of customized learning for different target samples. When the model encounters complex target distributi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06665v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06665v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06665v1-abstract-full" style="display: none;"> Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain strategies for target samples to adapt, ignoring the exploration of customized learning for different target samples. When the model encounters complex target distribution, existing methods will perform limited due to the inability to clearly and comprehensively learn the knowledge of multiple types of target samples. To fill this gap, this paper focuses on designing a framework to use different strategies for comprehensively mining different target samples. We propose a novel source-free framework (SOUF) to achieve semi-supervised fine-tuning of the source pre-trained model on the target domain. Different from existing SSDA methods, SOUF decouples SSDA from the perspectives of different target samples, specifically designing robust learning techniques for unlabeled, reliably labeled, and noisy pseudo-labeled target samples. For unlabeled target samples, probability-based weighted contrastive learning (PWC) helps the model learn more discriminative feature representations. To mine the latent knowledge of labeled target samples, reliability-based mixup contrastive learning (RMC) learns complex knowledge from the constructed reliable sample set. Finally, predictive regularization learning (PR) further mitigates the misleading effect of noisy pseudo-labeled samples on the model. Extensive experiments on benchmark datasets demonstrate the superiority of our framework over state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06665v1-abstract-full').style.display = 'none'; document.getElementById('2411.06665v1-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/2411.05311">arXiv:2411.05311</a> <span> [<a href="https://arxiv.org/pdf/2411.05311">pdf</a>, <a href="https://arxiv.org/format/2411.05311">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tao Ma</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+H">Hongbin Zhou</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Q">Qiusheng Huang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xuemeng Yang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jianfei Guo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+M">Min Dou</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+B">Botian Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongsheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05311v1-abstract-short" style="display: inline;"> Offboard perception aims to automatically generate high-quality 3D labels for autonomous driving (AD) scenes. Existing offboard methods focus on 3D object detection with closed-set taxonomy and fail to match human-level recognition capability on the rapidly evolving perception tasks. Due to heavy reliance on human labels and the prevalence of data imbalance and sparsity, a unified framework for of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05311v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05311v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05311v1-abstract-full" style="display: none;"> Offboard perception aims to automatically generate high-quality 3D labels for autonomous driving (AD) scenes. Existing offboard methods focus on 3D object detection with closed-set taxonomy and fail to match human-level recognition capability on the rapidly evolving perception tasks. Due to heavy reliance on human labels and the prevalence of data imbalance and sparsity, a unified framework for offboard auto-labeling various elements in AD scenes that meets the distinct needs of perception tasks is not being fully explored. In this paper, we propose a novel multi-modal Zero-shot Offboard Panoptic Perception (ZOPP) framework for autonomous driving scenes. ZOPP integrates the powerful zero-shot recognition capabilities of vision foundation models and 3D representations derived from point clouds. To the best of our knowledge, ZOPP represents a pioneering effort in the domain of multi-modal panoptic perception and auto labeling for autonomous driving scenes. We conduct comprehensive empirical studies and evaluations on Waymo open dataset to validate the proposed ZOPP on various perception tasks. To further explore the usability and extensibility of our proposed ZOPP, we also conduct experiments in downstream applications. The results further demonstrate the great potential of our ZOPP for real-world scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05311v1-abstract-full').style.display = 'none'; document.getElementById('2411.05311v1-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">Accepted by NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04847">arXiv:2411.04847</a> <span> [<a href="https://arxiv.org/pdf/2411.04847">pdf</a>, <a href="https://arxiv.org/format/2411.04847">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"> Prompt-Guided Internal States for Hallucination Detection of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+F">Fujie Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P">Peiqi Yu</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+B">Biao Yi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baolei Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tong Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zheli 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="2411.04847v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on spec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04847v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04847v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04847v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes in the structure related to text truthfulness within the LLM's internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04847v1-abstract-full').style.display = 'none'; document.getElementById('2411.04847v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04571">arXiv:2411.04571</a> <span> [<a href="https://arxiv.org/pdf/2411.04571">pdf</a>, <a href="https://arxiv.org/format/2411.04571">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"> DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Duan%2C+Y">Yuxuan Duan</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+Y">Yan Hong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Lan%2C+J">Jun Lan</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Huijia Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weiqiang Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianfu Zhang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Li Niu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Liqing 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="2411.04571v1-abstract-short" style="display: inline;"> The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when we expect to generate images that fall into a specific domain either hard to describe or just unseen to the models. In this work, we propose DomainGa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04571v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04571v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04571v1-abstract-full" style="display: none;"> The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when we expect to generate images that fall into a specific domain either hard to describe or just unseen to the models. In this work, we propose DomainGallery, a few-shot domain-driven image generation method which aims at finetuning pretrained Stable Diffusion on few-shot target datasets in an attribute-centric manner. Specifically, DomainGallery features prior attribute erasure, attribute disentanglement, regularization and enhancement. These techniques are tailored to few-shot domain-driven generation in order to solve key issues that previous works have failed to settle. Extensive experiments are given to validate the superior performance of DomainGallery on a variety of domain-driven generation scenarios. Codes are available at https://github.com/Ldhlwh/DomainGallery. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04571v1-abstract-full').style.display = 'none'; document.getElementById('2411.04571v1-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">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/2411.04356">arXiv:2411.04356</a> <span> [<a href="https://arxiv.org/pdf/2411.04356">pdf</a>, <a href="https://arxiv.org/format/2411.04356">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"> GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuangjie Li</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jiangqing Song</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baoming Zhang</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+G">Gaoli Ruan</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+J">Junyuan Xie</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chongjun 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="2411.04356v1-abstract-short" style="display: inline;"> Graph neural networks (GNNs) are prominent for their effectiveness in processing graph data for semi-supervised node classification tasks. Most works of GNNs assume that the observed structure accurately represents the underlying node relationships. However, the graph structure is inevitably noisy or incomplete in reality, which can degrade the quality of graph representations. Therefore, it is im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04356v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04356v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04356v1-abstract-full" style="display: none;"> Graph neural networks (GNNs) are prominent for their effectiveness in processing graph data for semi-supervised node classification tasks. Most works of GNNs assume that the observed structure accurately represents the underlying node relationships. However, the graph structure is inevitably noisy or incomplete in reality, which can degrade the quality of graph representations. Therefore, it is imperative to learn a clean graph structure that balances performance and robustness. In this paper, we propose a novel method named \textit{Global-augmented Graph Structure Learning} (GaGSL), guided by the Graph Information Bottleneck (GIB) principle. The key idea behind GaGSL is to learn a compact and informative graph structure for node classification tasks. Specifically, to mitigate the bias caused by relying solely on the original structure, we first obtain augmented features and augmented structure through global feature augmentation and global structure augmentation. We then input the augmented features and augmented structure into a structure estimator with different parameters for optimization and re-definition of the graph structure, respectively. The redefined structures are combined to form the final graph structure. Finally, we employ GIB based on mutual information to guide the optimization of the graph structure to obtain the minimum sufficient graph structure. Comprehensive evaluations across a range of datasets reveal the outstanding performance and robustness of GaGSL compared with the state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04356v1-abstract-full').style.display = 'none'; document.getElementById('2411.04356v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03744">arXiv:2411.03744</a> <span> [<a href="https://arxiv.org/pdf/2411.03744">pdf</a>, <a href="https://arxiv.org/format/2411.03744">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"> Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuangjie Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baoming Zhang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jianqing Song</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+G">Gaoli Ruan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chongjun Wang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+J">Junyuan Xie</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="2411.03744v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have gained considerable prominence in semi-supervised learning tasks in processing graph-structured data, primarily owing to their message-passing mechanism, which largely relies on the availability of clean labels. However, in real-world scenarios, labels on nodes of graphs are inevitably noisy and sparsely labeled, significantly degrading the performance of GNNs. Ex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03744v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03744v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03744v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have gained considerable prominence in semi-supervised learning tasks in processing graph-structured data, primarily owing to their message-passing mechanism, which largely relies on the availability of clean labels. However, in real-world scenarios, labels on nodes of graphs are inevitably noisy and sparsely labeled, significantly degrading the performance of GNNs. Exploring robust GNNs for semi-supervised node classification in the presence of noisy and sparse labels remains a critical challenge. Therefore, we propose a novel \textbf{G}raph \textbf{N}eural \textbf{N}etwork with \textbf{C}oarse- and \textbf{F}ine-\textbf{G}rained \textbf{D}ivision for mitigating label sparsity and noise, namely GNN-CFGD. The key idea of GNN-CFGD is reducing the negative impact of noisy labels via coarse- and fine-grained division, along with graph reconstruction. Specifically, we first investigate the effectiveness of linking unlabeled nodes to cleanly labeled nodes, demonstrating that this approach is more effective in combating labeling noise than linking to potentially noisy labeled nodes. Based on this observation, we introduce a Gaussian Mixture Model (GMM) based on the memory effect to perform a coarse-grained division of the given labels into clean and noisy labels. Next, we propose a clean labels oriented link that connects unlabeled nodes to cleanly labeled nodes, aimed at mitigating label sparsity and promoting supervision propagation. Furthermore, to provide refined supervision for noisy labeled nodes and additional supervision for unlabeled nodes, we fine-grain the noisy labeled and unlabeled nodes into two candidate sets based on confidence, respectively. Extensive experiments on various datasets demonstrate the superior effectiveness and robustness of GNN-CFGD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03744v1-abstract-full').style.display = 'none'; document.getElementById('2411.03744v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03675">arXiv:2411.03675</a> <span> [<a href="https://arxiv.org/pdf/2411.03675">pdf</a>, <a href="https://arxiv.org/format/2411.03675">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"> QUILL: Quotation Generation Enhancement of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Jin Xiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowei Zhang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Q">Qianyu He</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+J">Jiaqing Liang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+F">Feng Wei</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jinglei Chen</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Z">Zujie Liang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Deqing Yang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yanghua Xiao</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="2411.03675v1-abstract-short" style="display: inline;"> While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed human expectations. To bridge the gap, we systematically study how to evaluate and improve LLMs' performance in quotation generation tasks. We first establish a hol… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03675v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03675v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03675v1-abstract-full" style="display: none;"> While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed human expectations. To bridge the gap, we systematically study how to evaluate and improve LLMs' performance in quotation generation tasks. We first establish a holistic and automatic evaluation system for quotation generation task, which consists of five criteria each with corresponding automatic metric. To improve the LLMs' quotation generation abilities, we construct a bilingual knowledge base that is broad in scope and rich in dimensions, containing up to 32,022 quotes. Moreover, guided by our critiria, we further design a quotation-specific metric to rerank the retrieved quotations from the knowledge base. Extensive experiments show that our metrics strongly correlate with human preferences. Existing LLMs struggle to generate desired quotes, but our quotation knowledge base and reranking metric help narrow this gap. Our dataset and code are publicly available at https://github.com/GraceXiaoo/QUILL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03675v1-abstract-full').style.display = 'none'; document.getElementById('2411.03675v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <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, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02715">arXiv:2411.02715</a> <span> [<a href="https://arxiv.org/pdf/2411.02715">pdf</a>, <a href="https://arxiv.org/format/2411.02715">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"> CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ge%2C+J">Jinchao Ge</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Akide Liu</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+M+H">Minh Hieu Phan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qi Chen</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+Y">Yangyang Shu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yang 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="2411.02715v1-abstract-short" style="display: inline;"> Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest data. However, bypassing iterative distillation by directly transferring outputs of initial classes to the current learning task is not supported in existing clas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02715v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02715v1-abstract-full" style="display: none;"> Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest data. However, bypassing iterative distillation by directly transferring outputs of initial classes to the current learning task is not supported in existing class-specific CSS methods. Via Softmax, they enforce dependency between classes and adjust the output distribution at each learning step, resulting in a large probability distribution gap between initial and current tasks. We introduce a simple, yet effective Class Independent Transformation (CIT) that converts the outputs of existing semantic segmentation models into class-independent forms with negligible cost or performance loss. By utilizing class-independent predictions facilitated by CIT, we establish an accumulative distillation framework, ensuring equitable incorporation of all class information. We conduct extensive experiments on various segmentation architectures, including DeepLabV3, Mask2Former, and SegViTv2. Results from these experiments show minimal task forgetting across different datasets, with less than 5% for ADE20K in the most challenging 11 task configurations and less than 1% across all configurations for the PASCAL VOC 2012 dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02715v1-abstract-full').style.display = 'none'; document.getElementById('2411.02715v1-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">11 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/2411.02293">arXiv:2411.02293</a> <span> [<a href="https://arxiv.org/pdf/2411.02293">pdf</a>, <a href="https://arxiv.org/format/2411.02293">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xianghui Yang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+H">Huiwen Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiacheng Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hongxu Zhao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinhai Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinzhou Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qingxiang Lin</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jiaao Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Lifu Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sicong Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuhong Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yong Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Di Wang</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> </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="2411.02293v2-abstract-short" style="display: inline;"> While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D-1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02293v2-abstract-full').style.display = 'inline'; document.getElementById('2411.02293v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02293v2-abstract-full" style="display: none;"> While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D-1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-view to multi-view reconstruction. In the second stage, we introduce a feed-forward reconstruction model that rapidly and faithfully reconstructs the 3D asset given the generated multi-view images in approximately 7 seconds. The reconstruction network learns to handle noises and in-consistency introduced by the multi-view diffusion and leverages the available information from the condition image to efficiently recover the 3D structure. Our framework involves the text-to-image model, i.e., Hunyuan-DiT, making it a unified framework to support both text- and image-conditioned 3D generation. Our standard version has 3x more parameters than our lite and other existing model. Our Hunyuan3D-1.0 achieves an impressive balance between speed and quality, significantly reducing generation time while maintaining the quality and diversity of the produced assets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02293v2-abstract-full').style.display = 'none'; document.getElementById('2411.02293v2-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 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">Technical Report; 3D Generation</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00508">arXiv:2411.00508</a> <span> [<a href="https://arxiv.org/pdf/2411.00508">pdf</a>, <a href="https://arxiv.org/format/2411.00508">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"> CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kang%2C+G">Gi-Cheon Kang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Junghyun Kim</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+K">Kyuhwan Shim</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J+K">Jun Ki Lee</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Byoung-Tak 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="2411.00508v1-abstract-short" style="display: inline;"> This paper explores how non-experts can teach robots desired skills in their environments. We argue that natural language is an intuitive and accessible interface for robot learning. To this end, we investigate two key aspects: (1) how non-experts collect robotic data using natural language supervision and (2) how pre-trained vision-language models learn end-to-end policies directly from this supe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00508v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00508v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00508v1-abstract-full" style="display: none;"> This paper explores how non-experts can teach robots desired skills in their environments. We argue that natural language is an intuitive and accessible interface for robot learning. To this end, we investigate two key aspects: (1) how non-experts collect robotic data using natural language supervision and (2) how pre-trained vision-language models learn end-to-end policies directly from this supervision. We propose a data collection framework that collects robot demonstrations based on natural language supervision (e.g., "move forward") and further augments these demonstrations. Next, we introduce a model that learns language-conditioned policies from natural language supervision called CLIP-RT. Our model employs pre-trained CLIP models and learns to predict actions represented in language via contrastive imitation learning. We first train CLIP-RT on large-scale robotic data and then enable it to learn desired skills using data collected from our framework. CLIP-RT shows strong capabilities in acquiring novel manipulation skills, outperforming the state-of-the-art model, OpenVLA (7B parameters), by 17% in average success rates, while using 7x fewer parameters (1B). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00508v1-abstract-full').style.display = 'none'; document.getElementById('2411.00508v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">27 pages, 27 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23663">arXiv:2410.23663</a> <span> [<a href="https://arxiv.org/pdf/2410.23663">pdf</a>, <a href="https://arxiv.org/format/2410.23663">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> DIP: Diffusion Learning of Inconsistency Pattern for General DeepFake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nie%2C+F">Fan Nie</a>, <a href="/search/cs?searchtype=author&query=Ni%2C+J">Jiangqun Ni</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bin Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weizhe Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23663v1-abstract-short" style="display: inline;"> With the advancement of deepfake generation techniques, the importance of deepfake detection in protecting multimedia content integrity has become increasingly obvious. Recently, temporal inconsistency clues have been explored to improve the generalizability of deepfake video detection. According to our observation, the temporal artifacts of forged videos in terms of motion information usually exh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23663v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23663v1-abstract-full" style="display: none;"> With the advancement of deepfake generation techniques, the importance of deepfake detection in protecting multimedia content integrity has become increasingly obvious. Recently, temporal inconsistency clues have been explored to improve the generalizability of deepfake video detection. According to our observation, the temporal artifacts of forged videos in terms of motion information usually exhibits quite distinct inconsistency patterns along horizontal and vertical directions, which could be leveraged to improve the generalizability of detectors. In this paper, a transformer-based framework for Diffusion Learning of Inconsistency Pattern (DIP) is proposed, which exploits directional inconsistencies for deepfake video detection. Specifically, DIP begins with a spatiotemporal encoder to represent spatiotemporal information. A directional inconsistency decoder is adopted accordingly, where direction-aware attention and inconsistency diffusion are incorporated to explore potential inconsistency patterns and jointly learn the inherent relationships. In addition, the SpatioTemporal Invariant Loss (STI Loss) is introduced to contrast spatiotemporally augmented sample pairs and prevent the model from overfitting nonessential forgery artifacts. Extensive experiments on several public datasets demonstrate that our method could effectively identify directional forgery clues and achieve state-of-the-art performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23663v1-abstract-full').style.display = 'none'; document.getElementById('2410.23663v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, accepted with IEEE Trans. on Multimedia</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18558">arXiv:2410.18558</a> <span> [<a href="https://arxiv.org/pdf/2410.18558">pdf</a>, <a href="https://arxiv.org/format/2410.18558">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"> Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+S">Shuhao Gu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jialing Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Siyuan Zhou</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+K">Kevin Yu</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+Z">Zhaohu Xing</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liangdong Wang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Z">Zhou Cao</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+J">Jintao Jia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhuoyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yixuan Wang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhenchong Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo-Wen Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jijie Li</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+D">Dong Liang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yingli Zhao</a>, <a href="/search/cs?searchtype=author&query=Ao%2C+Y">Yulong Ao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yaoqi Liu</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+F">Fangxiang Feng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Guang 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="2410.18558v1-abstract-short" style="display: inline;"> Vision-Language Models (VLMs) have recently made significant progress, but the limited scale and quality of open-source instruction data hinder their performance compared to closed-source models. In this work, we address this limitation by introducing Infinity-MM, a large-scale multimodal instruction dataset with 40 million samples, enhanced through rigorous quality filtering and deduplication. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18558v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18558v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18558v1-abstract-full" style="display: none;"> Vision-Language Models (VLMs) have recently made significant progress, but the limited scale and quality of open-source instruction data hinder their performance compared to closed-source models. In this work, we address this limitation by introducing Infinity-MM, a large-scale multimodal instruction dataset with 40 million samples, enhanced through rigorous quality filtering and deduplication. We also propose a synthetic instruction generation method based on open-source VLMs, using detailed image annotations and diverse question generation. Using this data, we trained a 2-billion-parameter VLM, Aquila-VL-2B, achieving state-of-the-art (SOTA) performance for models of similar scale. This demonstrates that expanding instruction data and generating synthetic data can significantly improve the performance of open-source models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18558v1-abstract-full').style.display = 'none'; document.getElementById('2410.18558v1-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/2410.18505">arXiv:2410.18505</a> <span> [<a href="https://arxiv.org/pdf/2410.18505">pdf</a>, <a href="https://arxiv.org/format/2410.18505">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"> CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liangdong Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo-Wen Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chengwei Wu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hanyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xiaofeng Shi</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+S">Shuhao Gu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jijie Li</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Q">Quanyue Ma</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+T">TengFei Pan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Guang 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="2410.18505v2-abstract-short" style="display: inline;"> We present CCI3.0-HQ (https://huggingface.co/datasets/BAAI/CCI3-HQ), a high-quality 500GB subset of the Chinese Corpora Internet 3.0 (CCI3.0)(https://huggingface.co/datasets/BAAI/CCI3-Data), developed using a novel two-stage hybrid filtering pipeline that significantly enhances data quality. To evaluate its effectiveness, we trained a 0.5B parameter model from scratch on 100B tokens across various… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18505v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18505v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18505v2-abstract-full" style="display: none;"> We present CCI3.0-HQ (https://huggingface.co/datasets/BAAI/CCI3-HQ), a high-quality 500GB subset of the Chinese Corpora Internet 3.0 (CCI3.0)(https://huggingface.co/datasets/BAAI/CCI3-Data), developed using a novel two-stage hybrid filtering pipeline that significantly enhances data quality. To evaluate its effectiveness, we trained a 0.5B parameter model from scratch on 100B tokens across various datasets, achieving superior performance on 10 benchmarks in a zero-shot setting compared to CCI3.0, SkyPile, and WanjuanV1. The high-quality filtering process effectively distills the capabilities of the Qwen2-72B-instruct model into a compact 0.5B model, attaining optimal F1 scores for Chinese web data classification. We believe this open-access dataset will facilitate broader access to high-quality language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18505v2-abstract-full').style.display = 'none'; document.getElementById('2410.18505v2-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">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/2410.18472">arXiv:2410.18472</a> <span> [<a href="https://arxiv.org/pdf/2410.18472">pdf</a>, <a href="https://arxiv.org/format/2410.18472">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"> What If the Input is Expanded in OOD Detection? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boxuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jianing Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zengmao Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tongliang Liu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+B">Bo Du</a>, <a href="/search/cs?searchtype=author&query=Han%2C+B">Bo Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18472v2-abstract-short" style="display: inline;"> Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18472v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18472v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18472v2-abstract-full" style="display: none;"> Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits its representation dimension. In this work, we introduce a novel perspective, i.e., employing different common corruptions on the input space, to expand that. We reveal an interesting phenomenon termed confidence mutation, where the confidence of OOD data can decrease significantly under the corruptions, while the ID data shows a higher confidence expectation considering the resistance of semantic features. Based on that, we formalize a new scoring method, namely, Confidence aVerage (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different corrupted inputs and the original ones, making the OOD and ID distributions more separable in detection tasks. Extensive experiments and analyses have been conducted to understand and verify the effectiveness of CoVer. The code is publicly available at: https://github.com/tmlr-group/CoVer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18472v2-abstract-full').style.display = 'none'; document.getElementById('2410.18472v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted by NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17971">arXiv:2410.17971</a> <span> [<a href="https://arxiv.org/pdf/2410.17971">pdf</a>, <a href="https://arxiv.org/format/2410.17971">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <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"> Dynamic Spectrum Access for Ambient Backscatter Communication-assisted D2D Systems with Quantum Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Huynh%2C+N">Nguyen Van Huynh</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bolun Zhang</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+D">Dinh-Hieu Tran</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D+T">Dinh Thai Hoang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+N">Diep N. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+G">Gan Zheng</a>, <a href="/search/cs?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+Q">Quoc-Viet Pham</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="2410.17971v1-abstract-short" style="display: inline;"> Spectrum access is an essential problem in device-to-device (D2D) communications. However, with the recent growth in the number of mobile devices, the wireless spectrum is becoming scarce, resulting in low spectral efficiency for D2D communications. To address this problem, this paper aims to integrate the ambient backscatter communication technology into D2D devices to allow them to backscatter a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17971v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17971v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17971v1-abstract-full" style="display: none;"> Spectrum access is an essential problem in device-to-device (D2D) communications. However, with the recent growth in the number of mobile devices, the wireless spectrum is becoming scarce, resulting in low spectral efficiency for D2D communications. To address this problem, this paper aims to integrate the ambient backscatter communication technology into D2D devices to allow them to backscatter ambient RF signals to transmit their data when the shared spectrum is occupied by mobile users. To obtain the optimal spectrum access policy, i.e., stay idle or access the shared spectrum and perform active transmissions or backscattering ambient RF signals for transmissions, to maximize the average throughput for D2D users, deep reinforcement learning (DRL) can be adopted. However, DRL-based solutions may require long training time due to the curse of dimensionality issue as well as complex deep neural network architectures. For that, we develop a novel quantum reinforcement learning (RL) algorithm that can achieve a faster convergence rate with fewer training parameters compared to DRL thanks to the quantum superposition and quantum entanglement principles. Specifically, instead of using conventional deep neural networks, the proposed quantum RL algorithm uses a parametrized quantum circuit to approximate an optimal policy. Extensive simulations then demonstrate that the proposed solution not only can significantly improve the average throughput of D2D devices when the shared spectrum is busy but also can achieve much better performance in terms of convergence rate and learning complexity compared to existing DRL-based methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17971v1-abstract-full').style.display = 'none'; document.getElementById('2410.17971v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 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">12 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/2410.17514">arXiv:2410.17514</a> <span> [<a href="https://arxiv.org/pdf/2410.17514">pdf</a>, <a href="https://arxiv.org/format/2410.17514">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"> SRA: A Novel Method to Improve Feature Embedding in Self-supervised Learning for Histopathological Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Manoochehri%2C+H">Hamid Manoochehri</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bodong Zhang</a>, <a href="/search/cs?searchtype=author&query=Knudsen%2C+B+S">Beatrice S. Knudsen</a>, <a href="/search/cs?searchtype=author&query=Tasdizen%2C+T">Tolga Tasdizen</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="2410.17514v3-abstract-short" style="display: inline;"> Self-supervised learning has become a cornerstone in various areas, particularly histopathological image analysis. Image augmentation plays a crucial role in self-supervised learning, as it generates variations in image samples. However, traditional image augmentation techniques often overlook the unique characteristics of histopathological images. In this paper, we propose a new histopathology-sp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17514v3-abstract-full').style.display = 'inline'; document.getElementById('2410.17514v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17514v3-abstract-full" style="display: none;"> Self-supervised learning has become a cornerstone in various areas, particularly histopathological image analysis. Image augmentation plays a crucial role in self-supervised learning, as it generates variations in image samples. However, traditional image augmentation techniques often overlook the unique characteristics of histopathological images. In this paper, we propose a new histopathology-specific image augmentation method called stain reconstruction augmentation (SRA). We integrate our SRA with MoCo v3, a leading model in self-supervised contrastive learning, along with our additional contrastive loss terms, and call the new model SRA-MoCo v3. We demonstrate that our SRA-MoCo v3 always outperforms the standard MoCo v3 across various downstream tasks and achieves comparable or superior performance to other foundation models pre-trained on significantly larger histopathology datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17514v3-abstract-full').style.display = 'none'; document.getElementById('2410.17514v3-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 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Hamid Manoochehri and Bodong Zhang contributed equally to this work</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17267">arXiv:2410.17267</a> <span> [<a href="https://arxiv.org/pdf/2410.17267">pdf</a>, <a href="https://arxiv.org/format/2410.17267">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jeong%2C+S">Seongjun Jeong</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+G">Gi-Cheon Kang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Joochan Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Byoung-Tak Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17267v1-abstract-short" style="display: inline;"> We propose the zero-shot Vision-and-Language Navigation with Collision Mitigation (VLN-CM), which takes these considerations. VLN-CM is composed of four modules and predicts the direction and distance of the next movement at each step. We utilize large foundation models for each modules. To select the direction, we use the Attention Spot Predictor (ASP), View Selector (VS), and Progress Monitor (P… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17267v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17267v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17267v1-abstract-full" style="display: none;"> We propose the zero-shot Vision-and-Language Navigation with Collision Mitigation (VLN-CM), which takes these considerations. VLN-CM is composed of four modules and predicts the direction and distance of the next movement at each step. We utilize large foundation models for each modules. To select the direction, we use the Attention Spot Predictor (ASP), View Selector (VS), and Progress Monitor (PM). The ASP employs a Large Language Model (e.g. ChatGPT) to split navigation instructions into attention spots, which are objects or scenes at the location to move to (e.g. a yellow door). The VS selects from panorama images provided at 30-degree intervals the one that includes the attention spot, using CLIP similarity. We then choose the angle of the selected image as the direction to move in. The PM uses a rule-based approach to decide which attention spot to focus on next, among multiple spots derived from the instructions. If the similarity between the current attention spot and the visual observations decreases consecutively at each step, the PM determines that the agent has passed the current spot and moves on to the next one. For selecting the distance to move, we employed the Open Map Predictor (OMP). The OMP uses panorama depth information to predict an occupancy mask. We then selected a collision-free distance in the predicted direction based on the occupancy mask. We evaluated our method using the validation data of VLN-CE. Our approach showed better performance than several baseline methods, and the OPM was effective in mitigating collisions for the agent. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17267v1-abstract-full').style.display = 'none'; document.getElementById('2410.17267v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16198">arXiv:2410.16198</a> <span> [<a href="https://arxiv.org/pdf/2410.16198">pdf</a>, <a href="https://arxiv.org/format/2410.16198">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Improve Vision Language Model Chain-of-thought Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruohong Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanghao Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haotian Zhang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Z">Zhiqing Sun</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+Z">Zhe Gan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yinfei Yang</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+R">Ruoming Pang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yiming Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.16198v1-abstract-short" style="display: inline;"> Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16198v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16198v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16198v1-abstract-full" style="display: none;"> Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses. To address this, we propose a two-fold approach. First, we distill rationales from GPT-4o model to enrich the training data and fine-tune VLMs, boosting their CoT performance. Second, we apply reinforcement learning to further calibrate reasoning quality. Specifically, we construct positive (correct) and negative (incorrect) pairs of model-generated reasoning chains, by comparing their predictions with annotated short answers. Using this pairwise data, we apply the Direct Preference Optimization algorithm to refine the model's reasoning abilities. Our experiments demonstrate significant improvements in CoT reasoning on benchmark datasets and better generalization to direct answer prediction as well. This work emphasizes the importance of incorporating detailed rationales in training and leveraging reinforcement learning to strengthen the reasoning capabilities of VLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16198v1-abstract-full').style.display = 'none'; document.getElementById('2410.16198v1-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">10 pages + appendix</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15716">arXiv:2410.15716</a> <span> [<a href="https://arxiv.org/pdf/2410.15716">pdf</a>, <a href="https://arxiv.org/format/2410.15716">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="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xinyu Yuan</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yan Qiao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+P">Pei Zhao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+R">Rongyao Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Benchu Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15716v1-abstract-short" style="display: inline;"> The traffic matrix estimation (TME) problem has been widely researched for decades of years. Recent progresses in deep generative models offer new opportunities to tackle TME problems in a more advanced way. In this paper, we leverage the powerful ability of denoising diffusion probabilistic models (DDPMs) on distribution learning, and for the first time adopt DDPM to address the TME problem. To e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15716v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15716v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15716v1-abstract-full" style="display: none;"> The traffic matrix estimation (TME) problem has been widely researched for decades of years. Recent progresses in deep generative models offer new opportunities to tackle TME problems in a more advanced way. In this paper, we leverage the powerful ability of denoising diffusion probabilistic models (DDPMs) on distribution learning, and for the first time adopt DDPM to address the TME problem. To ensure a good performance of DDPM on learning the distributions of TMs, we design a preprocessing module to reduce the dimensions of TMs while keeping the data variety of each OD flow. To improve the estimation accuracy, we parameterize the noise factors in DDPM and transform the TME problem into a gradient-descent optimization problem. Finally, we compared our method with the state-of-the-art TME methods using two real-world TM datasets, the experimental results strongly demonstrate the superiority of our method on both TM synthesis and TM estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15716v1-abstract-full').style.display = 'none'; document.getElementById('2410.15716v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14913">arXiv:2410.14913</a> <span> [<a href="https://arxiv.org/pdf/2410.14913">pdf</a>, <a href="https://arxiv.org/format/2410.14913">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 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/10.1145/3681765.3698452">10.1145/3681765.3698452 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> ReeFRAME: Reeb Graph based Trajectory Analysis Framework to Capture Top-Down and Bottom-Up Patterns of Life </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gudavalli%2C+C">Chandrakanth Gudavalli</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Levenson%2C+C">Connor Levenson</a>, <a href="/search/cs?searchtype=author&query=Lore%2C+K+G">Kin Gwn Lore</a>, <a href="/search/cs?searchtype=author&query=Manjunath%2C+B+S">B. S. Manjunath</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="2410.14913v1-abstract-short" style="display: inline;"> In this paper, we present ReeFRAME, a scalable Reeb graph-based framework designed to analyze vast volumes of GPS-enabled human trajectory data generated at 1Hz frequency. ReeFRAME models Patterns-of-life (PoL) at both the population and individual levels, utilizing Multi-Agent Reeb Graphs (MARGs) for population-level patterns and Temporal Reeb Graphs (TERGs) for individual trajectories. The frame… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14913v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14913v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14913v1-abstract-full" style="display: none;"> In this paper, we present ReeFRAME, a scalable Reeb graph-based framework designed to analyze vast volumes of GPS-enabled human trajectory data generated at 1Hz frequency. ReeFRAME models Patterns-of-life (PoL) at both the population and individual levels, utilizing Multi-Agent Reeb Graphs (MARGs) for population-level patterns and Temporal Reeb Graphs (TERGs) for individual trajectories. The framework's linear algorithmic complexity relative to the number of time points ensures scalability for anomaly detection. We validate ReeFRAME on six large-scale anomaly detection datasets, simulating real-time patterns with up to 500,000 agents over two months. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14913v1-abstract-full').style.display = 'none'; document.getElementById('2410.14913v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">GeoAnomalies Workshop @ ACM Sigspatial 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/2410.14493">arXiv:2410.14493</a> <span> [<a href="https://arxiv.org/pdf/2410.14493">pdf</a>, <a href="https://arxiv.org/format/2410.14493">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"> Safeguarding Blockchain Ecosystem: Understanding and Detecting Attack Transactions on Cross-chain Bridges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiajing Wu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+K">Kaixin Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+D">Dan Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bozhao Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhiying Wu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+J">Jianzhong Su</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="2410.14493v1-abstract-short" style="display: inline;"> Cross-chain bridges are essential decentralized applications (DApps) to facilitate interoperability between different blockchain networks. Unlike regular DApps, the functionality of cross-chain bridges relies on the collaboration of information both on and off the chain, which exposes them to a wider risk of attacks. According to our statistics, attacks on cross-chain bridges have resulted in loss… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14493v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14493v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14493v1-abstract-full" style="display: none;"> Cross-chain bridges are essential decentralized applications (DApps) to facilitate interoperability between different blockchain networks. Unlike regular DApps, the functionality of cross-chain bridges relies on the collaboration of information both on and off the chain, which exposes them to a wider risk of attacks. According to our statistics, attacks on cross-chain bridges have resulted in losses of nearly 4.3 billion dollars since 2021. Therefore, it is particularly necessary to understand and detect attacks on cross-chain bridges. In this paper, we collect the largest number of cross-chain bridge attack incidents to date, including 49 attacks that occurred between June 2021 and September 2024. Our analysis reveal that attacks against cross-chain business logic cause significantly more damage than those that do not. These cross-chain attacks exhibit different patterns compared to normal transactions in terms of call structure, which effectively indicates potential attack behaviors. Given the significant losses in these cases and the scarcity of related research, this paper aims to detect attacks against cross-chain business logic, and propose the BridgeGuard tool. Specifically, BridgeGuard models cross-chain transactions from a graph perspective, and employs a two-stage detection framework comprising global and local graph mining to identify attack patterns in cross-chain transactions. We conduct multiple experiments on the datasets with 203 attack transactions and 40,000 normal cross-chain transactions. The results show that BridgeGuard's reported recall score is 36.32\% higher than that of state-of-the-art tools and can detect unknown attack transactions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14493v1-abstract-full').style.display = 'none'; document.getElementById('2410.14493v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14390">arXiv:2410.14390</a> <span> [<a href="https://arxiv.org/pdf/2410.14390">pdf</a>, <a href="https://arxiv.org/format/2410.14390">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"> Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boning Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+D">Dongzhu Liu</a>, <a href="/search/cs?searchtype=author&query=Simeone%2C+O">Osvaldo Simeone</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guanchu Wang</a>, <a href="/search/cs?searchtype=author&query=Pezaros%2C+D">Dimitrios Pezaros</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+G">Guangxu 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="2410.14390v1-abstract-short" style="display: inline;"> To support real-world decision-making, it is crucial for models to be well-calibrated, i.e., to assign reliable confidence estimates to their predictions. Uncertainty quantification is particularly important in personalized federated learning (PFL), as participating clients typically have small local datasets, making it difficult to unambiguously determine optimal model parameters. Bayesian PFL (B… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14390v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14390v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14390v1-abstract-full" style="display: none;"> To support real-world decision-making, it is crucial for models to be well-calibrated, i.e., to assign reliable confidence estimates to their predictions. Uncertainty quantification is particularly important in personalized federated learning (PFL), as participating clients typically have small local datasets, making it difficult to unambiguously determine optimal model parameters. Bayesian PFL (BPFL) methods can potentially enhance calibration, but they often come with considerable computational and memory requirements due to the need to track the variances of all the individual model parameters. Furthermore, different clients may exhibit heterogeneous uncertainty levels owing to varying local dataset sizes and distributions. To address these challenges, we propose LR-BPFL, a novel BPFL method that learns a global deterministic model along with personalized low-rank Bayesian corrections. To tailor the local model to each client's inherent uncertainty level, LR-BPFL incorporates an adaptive rank selection mechanism. We evaluate LR-BPFL across a variety of datasets, demonstrating its advantages in terms of calibration, accuracy, as well as computational and memory requirements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14390v1-abstract-full').style.display = 'none'; document.getElementById('2410.14390v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14236">arXiv:2410.14236</a> <span> [<a href="https://arxiv.org/pdf/2410.14236">pdf</a>, <a href="https://arxiv.org/format/2410.14236">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> A Novel Method to Metigate Demographic and Expert Bias in ICD Coding with Causal Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bin Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Junli 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="2410.14236v1-abstract-short" style="display: inline;"> ICD(International Classification of Diseases) coding involves assigning ICD codes to patients visit based on their medical notes. Considering ICD coding as a multi-label text classification task, researchers have developed sophisticated methods. Despite progress, these models often suffer from label imbalance and may develop spurious correlations with demographic factors. Additionally, while human… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14236v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14236v1-abstract-full" style="display: none;"> ICD(International Classification of Diseases) coding involves assigning ICD codes to patients visit based on their medical notes. Considering ICD coding as a multi-label text classification task, researchers have developed sophisticated methods. Despite progress, these models often suffer from label imbalance and may develop spurious correlations with demographic factors. Additionally, while human coders assign ICD codes, the inclusion of irrelevant information from unrelated experts introduces biases. To combat these issues, we propose a novel method to mitigate Demographic and Expert biases in ICD coding through Causal Inference (DECI). We provide a novel causality-based interpretation in ICD Coding that models make predictions by three distinct pathways. And based counterfactual reasoning, DECI mitigate demographic and expert biases. Experimental results show that DECI outperforms state-of-the-art models, offering a significant advancement in accurate and unbiased ICD coding. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14236v1-abstract-full').style.display = 'none'; document.getElementById('2410.14236v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14088">arXiv:2410.14088</a> <span> [<a href="https://arxiv.org/pdf/2410.14088">pdf</a>, <a href="https://arxiv.org/format/2410.14088">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Overcoming Memory Constraints in Quantum Circuit Simulation with a High-Fidelity Compression Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+B">Bo Fang</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+F">Fanjiang Ye</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yida Gu</a>, <a href="/search/cs?searchtype=author&query=Tallent%2C+N">Nathan Tallent</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+G">Guangming Tan</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+D">Dingwen 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="2410.14088v1-abstract-short" style="display: inline;"> Full-state quantum circuit simulation requires exponentially increased memory size to store the state vector as the number of qubits scales, presenting significant limitations in classical computing systems. Our paper introduces BMQSim, a novel state vector quantum simulation framework that employs lossy compression to address the memory constraints on graphics processing unit (GPU) machines. BMQS… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14088v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14088v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14088v1-abstract-full" style="display: none;"> Full-state quantum circuit simulation requires exponentially increased memory size to store the state vector as the number of qubits scales, presenting significant limitations in classical computing systems. Our paper introduces BMQSim, a novel state vector quantum simulation framework that employs lossy compression to address the memory constraints on graphics processing unit (GPU) machines. BMQSim effectively tackles four major challenges for state-vector simulation with compression: frequent compression/decompression, high memory movement overhead, lack of dedicated error control, and unpredictable memory space requirements. Our work proposes an innovative strategy of circuit partitioning to significantly reduce the frequency of compression occurrences. We introduce a pipeline that seamlessly integrates compression with data movement while concealing its overhead. Additionally, BMQSim incorporates the first GPU-based lossy compression technique with point-wise error control. Furthermore, BMQSim features a two-level memory management system, ensuring efficient and stable execution. Our evaluations demonstrate that BMQSim can simulate the same circuit with over 10 times less memory usage on average, achieving fidelity over 0.99 and maintaining comparable simulation time to other state-of-the-art simulators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14088v1-abstract-full').style.display = 'none'; document.getElementById('2410.14088v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13837">arXiv:2410.13837</a> <span> [<a href="https://arxiv.org/pdf/2410.13837">pdf</a>, <a href="https://arxiv.org/format/2410.13837">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C+B+C">Chen Bo Calvin Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+Z">Zhang-Wei Hong</a>, <a href="/search/cs?searchtype=author&query=Pacchiano%2C+A">Aldo Pacchiano</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+P">Pulkit Agrawal</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="2410.13837v2-abstract-short" style="display: inline;"> Reward shaping is a critical component in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. While shaping rewards have been introduced to provide additional guidance, selecting effective shaping functions remains challenging and computationally expensive. This paper introduces Online Reward Selection and Policy Optimization (ORSO), a novel approa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13837v2-abstract-full').style.display = 'inline'; document.getElementById('2410.13837v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13837v2-abstract-full" style="display: none;"> Reward shaping is a critical component in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. While shaping rewards have been introduced to provide additional guidance, selecting effective shaping functions remains challenging and computationally expensive. This paper introduces Online Reward Selection and Policy Optimization (ORSO), a novel approach that frames shaping reward selection as an online model selection problem. ORSO employs principled exploration strategies to automatically identify promising shaping reward functions without human intervention, balancing exploration and exploitation with provable regret guarantees. We demonstrate ORSO's effectiveness across various continuous control tasks using the Isaac Gym simulator. Compared to traditional methods that fully evaluate each shaping reward function, ORSO significantly improves sample efficiency, reduces computational time, and consistently identifies high-quality reward functions that produce policies comparable to those generated by domain experts through hand-engineered rewards. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13837v2-abstract-full').style.display = 'none'; document.getElementById('2410.13837v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">preprint, 35 pages, 23 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13280">arXiv:2410.13280</a> <span> [<a href="https://arxiv.org/pdf/2410.13280">pdf</a>, <a href="https://arxiv.org/format/2410.13280">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"> Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Yanan Guo</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Ying Xie</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+Y">Ying Chang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Benkui Zhang</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+B">Bo Jia</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+L">Lin 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="2410.13280v1-abstract-short" style="display: inline;"> Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13280v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13280v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13280v1-abstract-full" style="display: none;"> Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to simultaneously generate view-consistent images and camera poses within forward-facing scenes. The effective of our model is demonstrated through extensive experiments conducted on both real and synthetic datasets. These experiments clearly illustrate that our model can effectively optimize neural scene representations while simultaneously resolving significant camera pose misalignments. The source code is available at https://github.com/Bistu3DV/hybridBA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13280v1-abstract-full').style.display = 'none'; document.getElementById('2410.13280v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Photonics Asia 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/2410.13185">arXiv:2410.13185</a> <span> [<a href="https://arxiv.org/pdf/2410.13185">pdf</a>, <a href="https://arxiv.org/format/2410.13185">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+L">Long Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+W">Weiwen Xu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jiayan Guo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+R">Ruochen Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xingxuan Li</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+Y">Yuqian Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boqiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yuming Jiang</a>, <a href="/search/cs?searchtype=author&query=Xin%2C+Y">Yifei Xin</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+R">Ronghao Dang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+D">Deli Zhao</a>, <a href="/search/cs?searchtype=author&query=Rong%2C+Y">Yu Rong</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+T">Tian Feng</a>, <a href="/search/cs?searchtype=author&query=Bing%2C+L">Lidong Bing</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="2410.13185v5-abstract-short" style="display: inline;"> Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research directions. Recent developments in large language models~(LLMs) suggest a promising avenue for automating the generation of novel research ideas. However, existin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13185v5-abstract-full').style.display = 'inline'; document.getElementById('2410.13185v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13185v5-abstract-full" style="display: none;"> Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research directions. Recent developments in large language models~(LLMs) suggest a promising avenue for automating the generation of novel research ideas. However, existing methods for idea generation either trivially prompt LLMs or directly expose LLMs to extensive literature without indicating useful information. Inspired by the research process of human researchers, we propose a Chain-of-Ideas~(CoI) agent, an LLM-based agent that organizes relevant literature in a chain structure to effectively mirror the progressive development in a research domain. This organization facilitates LLMs to capture the current advancements in research, thereby enhancing their ideation capabilities. Furthermore, we propose Idea Arena, an evaluation protocol that can comprehensively evaluate idea generation methods from different perspectives, aligning closely with the preferences of human researchers. Experimental results indicate that the CoI agent consistently outperforms other methods and shows comparable quality as humans in research idea generation. Moreover, our CoI agent is budget-friendly, with a minimum cost of \$0.50 to generate a candidate idea and its corresponding experimental design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13185v5-abstract-full').style.display = 'none'; document.getElementById('2410.13185v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 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">10 pages,5 figures, conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13099">arXiv:2410.13099</a> <span> [<a href="https://arxiv.org/pdf/2410.13099">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Adversarial Neural Networks in Medical Imaging Advancements and Challenges in Semantic Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+H">Houze Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+Y">Yanlin Xiang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yuxiang Hu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+A">Aoran Shen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yang Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13099v1-abstract-short" style="display: inline;"> Recent advancements in artificial intelligence (AI) have precipitated a paradigm shift in medical imaging, particularly revolutionizing the domain of brain imaging. This paper systematically investigates the integration of deep learning -- a principal branch of AI -- into the semantic segmentation of brain images. Semantic segmentation serves as an indispensable technique for the delineation of di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13099v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13099v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13099v1-abstract-full" style="display: none;"> Recent advancements in artificial intelligence (AI) have precipitated a paradigm shift in medical imaging, particularly revolutionizing the domain of brain imaging. This paper systematically investigates the integration of deep learning -- a principal branch of AI -- into the semantic segmentation of brain images. Semantic segmentation serves as an indispensable technique for the delineation of discrete anatomical structures and the identification of pathological markers, essential for the diagnosis of complex neurological disorders. Historically, the reliance on manual interpretation by radiologists, while noteworthy for its accuracy, is plagued by inherent subjectivity and inter-observer variability. This limitation becomes more pronounced with the exponential increase in imaging data, which traditional methods struggle to process efficiently and effectively. In response to these challenges, this study introduces the application of adversarial neural networks, a novel AI approach that not only automates but also refines the semantic segmentation process. By leveraging these advanced neural networks, our approach enhances the precision of diagnostic outputs, reducing human error and increasing the throughput of imaging data analysis. The paper provides a detailed discussion on how adversarial neural networks facilitate a more robust, objective, and scalable solution, thereby significantly improving diagnostic accuracies in neurological evaluations. This exploration highlights the transformative impact of AI on medical imaging, setting a new benchmark for future research and clinical practice in neurology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13099v1-abstract-full').style.display = 'none'; document.getElementById('2410.13099v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12928">arXiv:2410.12928</a> <span> [<a href="https://arxiv.org/pdf/2410.12928">pdf</a>, <a href="https://arxiv.org/format/2410.12928">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"> DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jingxiang Sun</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+C">Cheng Peng</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+R">Ruizhi Shao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Yuan-Chen Guo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xiaochen Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yangguang Li</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yanpei Cao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yebin 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="2410.12928v1-abstract-short" style="display: inline;"> We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming geometry sculpting optimization with a feed-forward multi-plane based reconstruction model, speeding up the process by 1000x. For texture refinement, we propose a tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12928v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12928v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12928v1-abstract-full" style="display: none;"> We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming geometry sculpting optimization with a feed-forward multi-plane based reconstruction model, speeding up the process by 1000x. For texture refinement, we propose a training-free IP-Adapter module that is conditioned on the enhanced multi-view images to enhance texture and geometry consistency, providing a 4x faster alternative to DreamCraft3D's DreamBooth fine-tuning. Experiments on diverse datasets demonstrate DreamCraft3D++'s ability to generate creative 3D assets with intricate geometry and realistic 360掳 textures, outperforming state-of-the-art image-to-3D methods in quality and speed. The full implementation will be open-sourced to enable new possibilities in 3D content creation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12928v1-abstract-full').style.display = 'none'; document.getElementById('2410.12928v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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://dreamcraft3dplus.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12857">arXiv:2410.12857</a> <span> [<a href="https://arxiv.org/pdf/2410.12857">pdf</a>, <a href="https://arxiv.org/format/2410.12857">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="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Enterprise Benchmarks for Large Language Model Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bing Zhang</a>, <a href="/search/cs?searchtype=author&query=Takeuchi%2C+M">Mikio Takeuchi</a>, <a href="/search/cs?searchtype=author&query=Kawahara%2C+R">Ryo Kawahara</a>, <a href="/search/cs?searchtype=author&query=Asthana%2C+S">Shubhi Asthana</a>, <a href="/search/cs?searchtype=author&query=Hossain%2C+M+M">Md. Maruf Hossain</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+G">Guang-Jie Ren</a>, <a href="/search/cs?searchtype=author&query=Soule%2C+K">Kate Soule</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yada 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="2410.12857v1-abstract-short" style="display: inline;"> The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be able to benchmark enterprise datasets for various tasks. This work presents a systematic exploration of benchmarking strategies tailored to LLM evaluation, focusing on the utilizat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12857v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12857v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12857v1-abstract-full" style="display: none;"> The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be able to benchmark enterprise datasets for various tasks. This work presents a systematic exploration of benchmarking strategies tailored to LLM evaluation, focusing on the utilization of domain-specific datasets and consisting of a variety of NLP tasks. The proposed evaluation framework encompasses 25 publicly available datasets from diverse enterprise domains like financial services, legal, cyber security, and climate and sustainability. The diverse performance of 13 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12857v1-abstract-full').style.display = 'none'; document.getElementById('2410.12857v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11764">arXiv:2410.11764</a> <span> [<a href="https://arxiv.org/pdf/2410.11764">pdf</a>, <a href="https://arxiv.org/format/2410.11764">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"> Octopus-Swimming-Like Robot with Soft Asymmetric Arms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bobing Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yiming Li</a>, <a href="/search/cs?searchtype=author&query=Xuan%2C+S">Sicheng Xuan</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+H+W">Hong Wei Ng</a>, <a href="/search/cs?searchtype=author&query=Liufu%2C+Y">Yuliang Liufu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Z">Zhiqiang Tang</a>, <a href="/search/cs?searchtype=author&query=Laschi%2C+C">Cecilia Laschi</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="2410.11764v1-abstract-short" style="display: inline;"> Underwater vehicles have seen significant development over the past seventy years. However, bio-inspired propulsion robots are still in their early stages and require greater interdisciplinary collaboration between biologists and roboticists. The octopus, one of the most intelligent marine animals, exhibits remarkable abilities such as camouflaging, exploring, and hunting while swimming with its a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11764v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11764v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11764v1-abstract-full" style="display: none;"> Underwater vehicles have seen significant development over the past seventy years. However, bio-inspired propulsion robots are still in their early stages and require greater interdisciplinary collaboration between biologists and roboticists. The octopus, one of the most intelligent marine animals, exhibits remarkable abilities such as camouflaging, exploring, and hunting while swimming with its arms. Although bio-inspired robotics researchers have aimed to replicate these abilities, the complexity of designing an eight-arm bionic swimming platform has posed challenges from the beginning. In this work, we propose a novel bionic robot swimming platform that combines asymmetric passive morphing arms with an umbrella-like quick-return mechanism. Using only two simple constant-speed motors, this design achieves efficient swimming by replicating octopus-like arm movements and stroke time ratios. The robot reached a peak speed of 314 mm/s during its second power stroke. This design reduces the complexity of traditional octopus-like swimming robot actuation systems while maintaining good swimming performance. It offers a more achievable and efficient platform for biologists and roboticists conducting more profound octopus-inspired robotic and biological studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11764v1-abstract-full').style.display = 'none'; document.getElementById('2410.11764v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11761">arXiv:2410.11761</a> <span> [<a href="https://arxiv.org/pdf/2410.11761">pdf</a>, <a href="https://arxiv.org/format/2410.11761">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Ying Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guoan Wang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+Y">Yuanfeng Ji</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanjun Li</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jin Ye</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tianbin Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bin Zhang</a>, <a href="/search/cs?searchtype=author&query=Pei%2C+N">Nana Pei</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+R">Rongshan Yu</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Junjun He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.11761v2-abstract-short" style="display: inline;"> Despite the progress made by multimodal large language models (MLLMs) in computational pathology, they remain limited by a predominant focus on patch-level analysis, missing essential contextual information at the whole-slide level. The lack of large-scale instruction datasets and the gigapixel scale of whole slide images (WSIs) pose significant developmental challenges. In this paper, we present… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11761v2-abstract-full').style.display = 'inline'; document.getElementById('2410.11761v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11761v2-abstract-full" style="display: none;"> Despite the progress made by multimodal large language models (MLLMs) in computational pathology, they remain limited by a predominant focus on patch-level analysis, missing essential contextual information at the whole-slide level. The lack of large-scale instruction datasets and the gigapixel scale of whole slide images (WSIs) pose significant developmental challenges. In this paper, we present SlideChat, the first vision-language assistant capable of understanding gigapixel whole-slide images, exhibiting excellent multimodal conversational capability and response complex instruction across diverse pathology scenarios. To support its development, we created SlideInstruction, the largest instruction-following dataset for WSIs consisting of 4.2K WSI captions and 176K VQA pairs with multiple categories. Furthermore, we propose SlideBench, a multimodal benchmark that incorporates captioning and VQA tasks to assess SlideChat's capabilities in varied clinical settings such as microscopy, diagnosis. Compared to both general and specialized MLLMs, SlideChat exhibits exceptional capabilities achieving state-of-the-art performance on 18 of 22 tasks. For example, it achieved an overall accuracy of 81.17% on SlideBench-VQA (TCGA), and 54.15% on SlideBench-VQA (BCNB). We will fully release SlideChat, SlideInstruction and SlideBench as open-source resources to facilitate research and development in computational pathology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11761v2-abstract-full').style.display = 'none'; document.getElementById('2410.11761v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11296">arXiv:2410.11296</a> <span> [<a href="https://arxiv.org/pdf/2410.11296">pdf</a>, <a href="https://arxiv.org/format/2410.11296">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Strategic and Fair Aggregator Interactions in Energy Markets: Mutli-agent Dynamics and Quasiconcave Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiayi Li</a>, <a href="/search/cs?searchtype=author&query=Motoki%2C+M">Matt Motoki</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Baosen Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.11296v1-abstract-short" style="display: inline;"> The introduction of aggregator structures has proven effective in bringing fairness to energy resource allocation by negotiating for more resources and economic surplus on behalf of users. This paper extends the fair energy resource allocation problem to a multi-agent setting, focusing on interactions among multiple aggregators in an electricity market. We prove that the strategic optimization p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11296v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11296v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11296v1-abstract-full" style="display: none;"> The introduction of aggregator structures has proven effective in bringing fairness to energy resource allocation by negotiating for more resources and economic surplus on behalf of users. This paper extends the fair energy resource allocation problem to a multi-agent setting, focusing on interactions among multiple aggregators in an electricity market. We prove that the strategic optimization problems faced by the aggregators form a quasiconcave game, ensuring the existence of a Nash equilibrium. This resolves complexities related to market price dependencies on total purchases and balancing fairness and efficiency in energy allocation. In addition, we design simulations to characterize the equilibrium points of the induced game, demonstrating how aggregators stabilize market outcomes, ensure fair resource distribution, and optimize user surplus. Our findings offer a robust framework for understanding strategic interactions among aggregators, contributing to more efficient and equitable energy markets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11296v1-abstract-full').style.display = 'none'; document.getElementById('2410.11296v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09924">arXiv:2410.09924</a> <span> [<a href="https://arxiv.org/pdf/2410.09924">pdf</a>, <a href="https://arxiv.org/format/2410.09924">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"> Conformalized Reachable Sets for Obstacle Avoidance With Spheres </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kwon%2C+Y">Yongseok Kwon</a>, <a href="/search/cs?searchtype=author&query=Michaux%2C+J">Jonathan Michaux</a>, <a href="/search/cs?searchtype=author&query=Isaacson%2C+S">Seth Isaacson</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bohao Zhang</a>, <a href="/search/cs?searchtype=author&query=Ejakov%2C+M">Matthew Ejakov</a>, <a href="/search/cs?searchtype=author&query=Skinner%2C+K+A">Katherine A. Skinner</a>, <a href="/search/cs?searchtype=author&query=Vasudevan%2C+R">Ram Vasudevan</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="2410.09924v1-abstract-short" style="display: inline;"> Safe motion planning algorithms are necessary for deploying autonomous robots in unstructured environments. Motion plans must be safe to ensure that the robot does not harm humans or damage any nearby objects. Generating these motion plans in real-time is also important to ensure that the robot can adapt to sudden changes in its environment. Many trajectory optimization methods introduce heuristic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09924v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09924v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09924v1-abstract-full" style="display: none;"> Safe motion planning algorithms are necessary for deploying autonomous robots in unstructured environments. Motion plans must be safe to ensure that the robot does not harm humans or damage any nearby objects. Generating these motion plans in real-time is also important to ensure that the robot can adapt to sudden changes in its environment. Many trajectory optimization methods introduce heuristics that balance safety and real-time performance, potentially increasing the risk of the robot colliding with its environment. This paper addresses this challenge by proposing Conformalized Reachable Sets for Obstacle Avoidance With Spheres (CROWS). CROWS is a novel real-time, receding-horizon trajectory planner that generates probalistically-safe motion plans. Offline, CROWS learns a novel neural network-based representation of a spherebased reachable set that overapproximates the swept volume of the robot's motion. CROWS then uses conformal prediction to compute a confidence bound that provides a probabilistic safety guarantee on the learned reachable set. At runtime, CROWS performs trajectory optimization to select a trajectory that is probabilstically-guaranteed to be collision-free. We demonstrate that CROWS outperforms a variety of state-of-the-art methods in solving challenging motion planning tasks in cluttered environments while remaining collision-free. Code, data, and video demonstrations can be found at https://roahmlab.github.io/crows/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09924v1-abstract-full').style.display = 'none'; document.getElementById('2410.09924v1-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 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">https://roahmlab.github.io/crows/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09873">arXiv:2410.09873</a> <span> [<a href="https://arxiv.org/pdf/2410.09873">pdf</a>, <a href="https://arxiv.org/format/2410.09873">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+H">Hancheng Ye</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+J">Jiakang Yuan</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+R">Renqiu Xia</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+X">Xiangchao Yan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tao Chen</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+J">Junchi Yan</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+B">Botian Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.09873v1-abstract-short" style="display: inline;"> Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09873v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09873v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09873v1-abstract-full" style="display: none;"> Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoised results identical to the original full-step ones. Specifically, the skipping strategy is guided by the third-order latent difference that indicates the stability between timesteps during the denoising process, which benefits the reusing of previous noise prediction results. Extensive experiments on image and video diffusion models demonstrate that our method can significantly speed up the denoising process while generating identical results to the original process, achieving up to an average 2~5x speedup without quality degradation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09873v1-abstract-full').style.display = 'none'; document.getElementById('2410.09873v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS 2024, Homepage: https://jiakangyuan.github.io/AdaptiveDiffusion-project-page/ The code is available at https://github.com/UniModal4Reasoning/AdaptiveDiffusion</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08035">arXiv:2410.08035</a> <span> [<a href="https://arxiv.org/pdf/2410.08035">pdf</a>, <a href="https://arxiv.org/format/2410.08035">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+X">Xiang Lyu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+Z">Zhihao Du</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qian Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Dong Zhang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Hangrui Hu</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+C">Chaohong Tan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Tianyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuxuan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bin Zhang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Heng Lu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yaqian Zhou</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+X">Xipeng Qiu</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="2410.08035v2-abstract-short" style="display: inline;"> Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions. To address this, we introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interacti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08035v2-abstract-full').style.display = 'inline'; document.getElementById('2410.08035v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08035v2-abstract-full" style="display: none;"> Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions. To address this, we introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. IntrinsicVoice aims to facilitate the transfer of textual capabilities of pre-trained LLMs to the speech modality by mitigating the modality gap between text and speech. Our novelty architecture, GroupFormer, can reduce speech sequences to lengths comparable to text sequences while generating high-quality audio, significantly reducing the length difference between speech and text, speeding up inference, and alleviating long-text modeling issues. Additionally, we construct a multi-turn speech-to-speech dialogue dataset named \method-500k which includes nearly 500k turns of speech-to-speech dialogues, and a cross-modality training strategy to enhance the semantic alignment between speech and text. Experimental results demonstrate that IntrinsicVoice can generate high-quality speech response with latency lower than 100ms in multi-turn dialogue scenarios. Demos are available at https://instrinsicvoice.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08035v2-abstract-full').style.display = 'none'; document.getElementById('2410.08035v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07737">arXiv:2410.07737</a> <span> [<a href="https://arxiv.org/pdf/2410.07737">pdf</a>, <a href="https://arxiv.org/format/2410.07737">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</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"> Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+C">Can Wang</a>, <a href="/search/cs?searchtype=author&query=Sui%2C+D">Dianbo Sui</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Hongliang Sun</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+H">Hao Ding</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bolin Zhang</a>, <a href="/search/cs?searchtype=author&query=Tu%2C+Z">Zhiying Tu</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="2410.07737v1-abstract-short" style="display: inline;"> Large Language Model (LLM) services exhibit impressive capability on unlearned tasks leveraging only a few examples by in-context learning (ICL). However, the success of ICL varies depending on the task and context, leading to heterogeneous service quality. Directly estimating the performance of LLM services at each invocation can be laborious, especially requiring abundant labeled data or interna… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07737v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07737v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07737v1-abstract-full" style="display: none;"> Large Language Model (LLM) services exhibit impressive capability on unlearned tasks leveraging only a few examples by in-context learning (ICL). However, the success of ICL varies depending on the task and context, leading to heterogeneous service quality. Directly estimating the performance of LLM services at each invocation can be laborious, especially requiring abundant labeled data or internal information within the LLM. This paper introduces a novel method to estimate the performance of LLM services across different tasks and contexts, which can be "plug-and-play" utilizing only a few unlabeled samples like ICL. Our findings suggest that the negative log-likelihood and perplexity derived from LLM service invocation can function as effective and significant features. Based on these features, we utilize four distinct meta-models to estimate the performance of LLM services. Our proposed method is compared against unlabeled estimation baselines across multiple LLM services and tasks. And it is experimentally applied to two scenarios, demonstrating its effectiveness in the selection and further optimization of LLM services. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07737v1-abstract-full').style.display = 'none'; document.getElementById('2410.07737v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07673">arXiv:2410.07673</a> <span> [<a href="https://arxiv.org/pdf/2410.07673">pdf</a>, <a href="https://arxiv.org/format/2410.07673">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"> Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jianxing Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shiqi Wang</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Han Yin</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Z">Zhenlong Sun</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+R">Ruobing Xie</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bo Zhang</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+Y">Yanghui Rao</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="2410.07673v1-abstract-short" style="display: inline;"> This paper focuses on detecting clickbait posts on the Web. These posts often use eye-catching disinformation in mixed modalities to mislead users to click for profit. That affects the user experience and thus would be blocked by content provider. To escape detection, malicious creators use tricks to add some irrelevant non-bait content into bait posts, dressing them up as legal to fool the detect… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07673v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07673v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07673v1-abstract-full" style="display: none;"> This paper focuses on detecting clickbait posts on the Web. These posts often use eye-catching disinformation in mixed modalities to mislead users to click for profit. That affects the user experience and thus would be blocked by content provider. To escape detection, malicious creators use tricks to add some irrelevant non-bait content into bait posts, dressing them up as legal to fool the detector. This content often has biased relations with non-bait labels, yet traditional detectors tend to make predictions based on simple co-occurrence rather than grasping inherent factors that lead to malicious behavior. This spurious bias would easily cause misjudgments. To address this problem, we propose a new debiased method based on causal inference. We first employ a set of features in multiple modalities to characterize the posts. Considering these features are often mixed up with unknown biases, we then disentangle three kinds of latent factors from them, including the invariant factor that indicates intrinsic bait intention; the causal factor which reflects deceptive patterns in a certain scenario, and non-causal noise. By eliminating the noise that causes bias, we can use invariant and causal factors to build a robust model with good generalization ability. Experiments on three popular datasets show the effectiveness of our approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07673v1-abstract-full').style.display = 'none'; document.getElementById('2410.07673v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07177">arXiv:2410.07177</a> <span> [<a href="https://arxiv.org/pdf/2410.07177">pdf</a>, <a href="https://arxiv.org/format/2410.07177">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> MM-Ego: Towards Building Egocentric Multimodal LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+H">Hanrong Ye</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haotian Zhang</a>, <a href="/search/cs?searchtype=author&query=Daxberger%2C+E">Erik Daxberger</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lin Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zongyu Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanghao Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=You%2C+H">Haoxuan You</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Dan Xu</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+Z">Zhe Gan</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiasen Lu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yinfei Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.07177v1-abstract-short" style="display: inline;"> This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we develop a data engine that efficiently generates 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long, based on human-a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07177v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07177v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07177v1-abstract-full" style="display: none;"> This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we develop a data engine that efficiently generates 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long, based on human-annotated data. This is currently the largest egocentric QA dataset. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a global glimpse step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we successfully build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07177v1-abstract-full').style.display = 'none'; document.getElementById('2410.07177v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Technical Report</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07135">arXiv:2410.07135</a> <span> [<a href="https://arxiv.org/pdf/2410.07135">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Causal Inference with Double/Debiased Machine Learning for Evaluating the Health Effects of Multiple Mismeasured Pollutants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+G">Gang Xu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xin Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Molin Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boya Zhang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wenhao Jiang</a>, <a href="/search/cs?searchtype=author&query=Laden%2C+F">Francine Laden</a>, <a href="/search/cs?searchtype=author&query=Suh%2C+H+H">Helen H. Suh</a>, <a href="/search/cs?searchtype=author&query=Szpiro%2C+A+A">Adam A. Szpiro</a>, <a href="/search/cs?searchtype=author&query=Spiegelman%2C+D">Donna Spiegelman</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zuoheng 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="2410.07135v1-abstract-short" style="display: inline;"> One way to quantify exposure to air pollution and its constituents in epidemiologic studies is to use an individual's nearest monitor. This strategy results in potential inaccuracy in the actual personal exposure, introducing bias in estimating the health effects of air pollution and its constituents, especially when evaluating the causal effects of correlated multi-pollutant constituents measured… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07135v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07135v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07135v1-abstract-full" style="display: none;"> One way to quantify exposure to air pollution and its constituents in epidemiologic studies is to use an individual's nearest monitor. This strategy results in potential inaccuracy in the actual personal exposure, introducing bias in estimating the health effects of air pollution and its constituents, especially when evaluating the causal effects of correlated multi-pollutant constituents measured with correlated error. This paper addresses estimation and inference for the causal effect of one constituent in the presence of other PM2.5 constituents, accounting for measurement error and correlations. We used a linear regression calibration model, fitted with generalized estimating equations in an external validation study, and extended a double/debiased machine learning (DML) approach to correct for measurement error and estimate the effect of interest in the main study. We demonstrated that the DML estimator with regression calibration is consistent and derived its asymptotic variance. Simulations showed that the proposed estimator reduced bias and attained nominal coverage probability across most simulation settings. We applied this method to assess the causal effects of PM2.5 constituents on cognitive function in the Nurses' Health Study and identified two PM2.5 constituents, Br and Mn, that showed a negative causal effect on cognitive function after measurement error correction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07135v1-abstract-full').style.display = 'none'; document.getElementById('2410.07135v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 September, 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/2410.06733">arXiv:2410.06733</a> <span> [<a href="https://arxiv.org/pdf/2410.06733">pdf</a>, <a href="https://arxiv.org/format/2410.06733">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qi Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bowen Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Gang Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qi Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.06733v1-abstract-short" style="display: inline;"> While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the complexity of assessing creative thought processes and the scarcity of relevant data. To address these challenges, we introduce SPLAT, a benchmark leveraging Situat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06733v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06733v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06733v1-abstract-full" style="display: none;"> While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the complexity of assessing creative thought processes and the scarcity of relevant data. To address these challenges, we introduce SPLAT, a benchmark leveraging Situation Puzzles to evaluate and elicit LAteral Thinking of LLMs. This benchmark, containing 975 graded situation puzzles across three difficulty levels, employs a new multi-turn player-judge framework instead of the traditional model-based evaluation, which often necessitates a stronger evaluation model. This framework simulates an interactive game where the model (player) asks the evaluation model (judge) questions about an incomplete story to infer the full scenario. The judge answers based on a detailed reference scenario or evaluates if the player's predictions align with the reference one. This approach lessens dependence on more robust evaluation models, enabling the assessment of state-of-the-art LLMs. The experiments demonstrate that a robust evaluation model, such as WizardLM-2, closely matches human judgements in both intermediate question-answering and final scenario accuracy, achieving over 80% agreement-similar to the agreement levels among humans. Furthermore, applying data and reasoning processes from our benchmark to other lateral thinking-related benchmarks, e.g., RiddleSense and BrainTeaser, leads to performance enhancements. This suggests that our benchmark effectively evaluates and elicits the lateral thinking abilities of LLMs. Code is available at: https://github.com/chenqi008/LateralThinking. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06733v1-abstract-full').style.display = 'none'; document.getElementById('2410.06733v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS 2024</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+B&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