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 1,516 results for author: <span class="mathjax">Shi, Y</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Shi%2C+Y">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Shi, Y"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Shi%2C+Y&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Shi, Y"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.21197">arXiv:2503.21197</a> <span> [<a href="https://arxiv.org/pdf/2503.21197">pdf</a>, <a href="https://arxiv.org/ps/2503.21197">ps</a>, <a href="https://arxiv.org/format/2503.21197">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</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"> WVSC: Wireless Video Semantic Communication with Multi-frame Compensation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xie%2C+B">Bingyan Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yongpeng Wu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuxuan Shi</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+B">Biqian Feng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jihong Park</a>, <a href="/search/cs?searchtype=author&query=Quek%2C+T+Q+S">Tony Q. S. Quek</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="2503.21197v1-abstract-short" style="display: inline;"> Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework, abbreviated as WVSC, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC first encodes original video frames as semantic fram… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21197v1-abstract-full').style.display = 'inline'; document.getElementById('2503.21197v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.21197v1-abstract-full" style="display: none;"> Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework, abbreviated as WVSC, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC first encodes original video frames as semantic frames and then conducts video coding based on such compact representations, enabling the video coding in semantic level rather than pixel level. Moreover, to further reduce the communication overhead, a reference semantic frame is introduced to substitute motion vectors of each frame in common video coding methods. At the receiver, multi-frame compensation (MFC) is proposed to produce compensated current semantic frame with a multi-frame fusion attention module. With both the reference frame transmission and MFC, the bandwidth efficiency improves with satisfying video transmission performance. Experimental results verify the performance gain of WVSC over other DL-based methods e.g. DVSC about 1 dB and traditional schemes about 2 dB in terms of PSNR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21197v1-abstract-full').style.display = 'none'; document.getElementById('2503.21197v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20483">arXiv:2503.20483</a> <span> [<a href="https://arxiv.org/pdf/2503.20483">pdf</a>, <a href="https://arxiv.org/format/2503.20483">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yingdong Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Changming Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yongxiang Zhao</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+A">Anqi Pang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sibei Yang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jingyi Yu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+K">Kan 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="2503.20483v1-abstract-short" style="display: inline;"> Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases can potentially contribute to harmful real-world consequences, reinforcing stereotypes and exacerbating inequalities in various social contexts. While existing r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20483v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20483v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20483v1-abstract-full" style="display: none;"> Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases can potentially contribute to harmful real-world consequences, reinforcing stereotypes and exacerbating inequalities in various social contexts. While existing research on diffusion bias mitigation has predominantly focused on guiding content generation, it often neglects the intrinsic mechanisms within diffusion models that causally drive biased outputs. In this paper, we investigate the internal processes of diffusion models, identifying specific decision-making mechanisms, termed bias features, embedded within the model architecture. By directly manipulating these features, our method precisely isolates and adjusts the elements responsible for bias generation, permitting granular control over the bias levels in the generated content. Through experiments on both unconditional and conditional diffusion models across various social bias attributes, we demonstrate our method's efficacy in managing generation distribution while preserving image quality. We also dissect the discovered model mechanism, revealing different intrinsic features controlling fine-grained aspects of generation, boosting further research on mechanistic interpretability of diffusion models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20483v1-abstract-full').style.display = 'none'; document.getElementById('2503.20483v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2025; Project Page: https://foundation-model-research.github.io/difflens</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20314">arXiv:2503.20314</a> <span> [<a href="https://arxiv.org/pdf/2503.20314">pdf</a>, <a href="https://arxiv.org/format/2503.20314">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"> Wan: Open and Advanced Large-Scale Video Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=WanTeam"> WanTeam</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+A">Ang Wang</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+B">Baole Ai</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+B">Bin Wen</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+C">Chaojie Mao</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+C">Chen-Wei Xie</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Di Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+F">Feiwu Yu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Haiming Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jianxiao Yang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+J">Jianyuan Zeng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiayu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jingfeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingren Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jinkai Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jixuan Chen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+K">Kai Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kang Zhao</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+K">Keyu Yan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+L">Lianghua Huang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+M">Mengyang Feng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+N">Ningyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pandeng Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+P">Pingyu Wu</a> , et al. (38 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="2503.20314v1-abstract-short" style="display: inline;"> This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20314v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20314v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20314v1-abstract-full" style="display: none;"> This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20314v1-abstract-full').style.display = 'none'; document.getElementById('2503.20314v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">60 pages, 33 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/2503.19625">arXiv:2503.19625</a> <span> [<a href="https://arxiv.org/pdf/2503.19625">pdf</a>, <a href="https://arxiv.org/format/2503.19625">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"> DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meng%2C+X">Xiangting Meng</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiaqi Yang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+M">Mingshu Chen</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+C">Chenxin Yan</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yujiao Shi</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+W">Wenchao Ding</a>, <a href="/search/cs?searchtype=author&query=Kneip%2C+L">Laurent Kneip</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="2503.19625v1-abstract-short" style="display: inline;"> In the realm of object pose estimation, scenarios involving both dynamic objects and moving cameras are prevalent. However, the scarcity of corresponding real-world datasets significantly hinders the development and evaluation of robust pose estimation models. This is largely attributed to the inherent challenges in accurately annotating object poses in dynamic scenes captured by moving cameras. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19625v1-abstract-full').style.display = 'inline'; document.getElementById('2503.19625v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.19625v1-abstract-full" style="display: none;"> In the realm of object pose estimation, scenarios involving both dynamic objects and moving cameras are prevalent. However, the scarcity of corresponding real-world datasets significantly hinders the development and evaluation of robust pose estimation models. This is largely attributed to the inherent challenges in accurately annotating object poses in dynamic scenes captured by moving cameras. To bridge this gap, this paper presents a novel dataset DynOPETs and a dedicated data acquisition and annotation pipeline tailored for object pose estimation and tracking in such unconstrained environments. Our efficient annotation method innovatively integrates pose estimation and pose tracking techniques to generate pseudo-labels, which are subsequently refined through pose graph optimization. The resulting dataset offers accurate pose annotations for dynamic objects observed from moving cameras. To validate the effectiveness and value of our dataset, we perform comprehensive evaluations using 18 state-of-the-art methods, demonstrating its potential to accelerate research in this challenging domain. The dataset will be made publicly available to facilitate further exploration and advancement in the field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19625v1-abstract-full').style.display = 'none'; document.getElementById('2503.19625v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18987">arXiv:2503.18987</a> <span> [<a href="https://arxiv.org/pdf/2503.18987">pdf</a>, <a href="https://arxiv.org/format/2503.18987">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiran Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian Zhang</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+L">Lei Qi</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yinghuan Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18987v1-abstract-short" style="display: inline;"> Domain generalization is proposed to address distribution shift, arising from statistical disparities between training source and unseen target domains. The widely used first-order meta-learning algorithms demonstrate strong performance for domain generalization by leveraging the gradient matching theory, which aims to establish balanced parameters across source domains to reduce overfitting to an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18987v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18987v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18987v1-abstract-full" style="display: none;"> Domain generalization is proposed to address distribution shift, arising from statistical disparities between training source and unseen target domains. The widely used first-order meta-learning algorithms demonstrate strong performance for domain generalization by leveraging the gradient matching theory, which aims to establish balanced parameters across source domains to reduce overfitting to any particular domain. However, our analysis reveals that there are actually numerous directions to achieve gradient matching, with current methods representing just one possible path. These methods actually overlook another critical factor that the balanced parameters should be close to the centroid of optimal parameters of each source domain. To address this, we propose a simple yet effective arithmetic meta-learning with arithmetic-weighted gradients. This approach, while adhering to the principles of gradient matching, promotes a more precise balance by estimating the centroid between domain-specific optimal parameters. Experimental results validate the effectiveness of our strategy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18987v1-abstract-full').style.display = 'none'; document.getElementById('2503.18987v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18680">arXiv:2503.18680</a> <span> [<a href="https://arxiv.org/pdf/2503.18680">pdf</a>, <a href="https://arxiv.org/format/2503.18680">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> ArchSeek: Retrieving Architectural Case Studies Using Vision-Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+D">Danrui Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yichao Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yaluo Wang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Ziying Shi</a>, <a href="/search/cs?searchtype=author&query=Kapadia%2C+M">Mubbasir Kapadia</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="2503.18680v1-abstract-short" style="display: inline;"> Efficiently searching for relevant case studies is critical in architectural design, as designers rely on precedent examples to guide or inspire their ongoing projects. However, traditional text-based search tools struggle to capture the inherently visual and complex nature of architectural knowledge, often leading to time-consuming and imprecise exploration. This paper introduces ArchSeek, an inn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18680v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18680v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18680v1-abstract-full" style="display: none;"> Efficiently searching for relevant case studies is critical in architectural design, as designers rely on precedent examples to guide or inspire their ongoing projects. However, traditional text-based search tools struggle to capture the inherently visual and complex nature of architectural knowledge, often leading to time-consuming and imprecise exploration. This paper introduces ArchSeek, an innovative case study search system with recommendation capability, tailored for architecture design professionals. Powered by the visual understanding capabilities from vision-language models and cross-modal embeddings, it enables text and image queries with fine-grained control, and interaction-based design case recommendations. It offers architects a more efficient, personalized way to discover design inspirations, with potential applications across other visually driven design fields. The source code is available at https://github.com/danruili/ArchSeek. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18680v1-abstract-full').style.display = 'none'; document.getElementById('2503.18680v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 8 figures, 3 tables. Accepted by CAAD Futures 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18349">arXiv:2503.18349</a> <span> [<a href="https://arxiv.org/pdf/2503.18349">pdf</a>, <a href="https://arxiv.org/format/2503.18349">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"> Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deng%2C+Z">Zekai Deng</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Ye Shi</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+K">Kaiyang Ji</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Lan Xu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+S">Shaoli Huang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingya 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="2503.18349v1-abstract-short" style="display: inline;"> Human-Object Interaction (HOI) is vital for advancing simulation, animation, and robotics, enabling the generation of long-term, physically plausible motions in 3D environments. However, existing methods often fall short of achieving physics realism and supporting diverse types of interactions. To address these challenges, this paper introduces a unified Human-Object Interaction framework that pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18349v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18349v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18349v1-abstract-full" style="display: none;"> Human-Object Interaction (HOI) is vital for advancing simulation, animation, and robotics, enabling the generation of long-term, physically plausible motions in 3D environments. However, existing methods often fall short of achieving physics realism and supporting diverse types of interactions. To address these challenges, this paper introduces a unified Human-Object Interaction framework that provides unified control over interactions with static scenes and dynamic objects using language commands. The interactions between human and object parts can always be described as the continuous stable Relative Movement Dynamics (RMD) between human and object parts. By leveraging the world knowledge and scene perception capabilities of Vision-Language Models (VLMs), we translate language commands into RMD diagrams, which are used to guide goal-conditioned reinforcement learning for sequential interaction with objects. Our framework supports long-horizon interactions among dynamic, articulated, and static objects. To support the training and evaluation of our framework, we present a new dataset named Interplay, which includes multi-round task plans generated by VLMs, covering both static and dynamic HOI tasks. Extensive experiments demonstrate that our proposed framework can effectively handle a wide range of HOI tasks, showcasing its ability to maintain long-term, multi-round transitions. For more details, please refer to our project webpage: https://rmd-hoi.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18349v1-abstract-full').style.display = 'none'; document.getElementById('2503.18349v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18336">arXiv:2503.18336</a> <span> [<a href="https://arxiv.org/pdf/2503.18336">pdf</a>, <a href="https://arxiv.org/format/2503.18336">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Rise of the Community Champions: From Reviewer Crunch to Community Power </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+C">Changlun Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yao Shi</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yuyu Luo</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+N">Nan Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18336v1-abstract-short" style="display: inline;"> Academic publishing is facing a crisis driven by exponential growth in submissions and an overwhelmed peer review system, leading to inconsistent decisions and a severe reviewer shortage. This paper introduces Panvas, a platform that reimagines academic publishing as a continuous, community-driven process. Panvas addresses these systemic failures with a novel combination of economic incentives (pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18336v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18336v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18336v1-abstract-full" style="display: none;"> Academic publishing is facing a crisis driven by exponential growth in submissions and an overwhelmed peer review system, leading to inconsistent decisions and a severe reviewer shortage. This paper introduces Panvas, a platform that reimagines academic publishing as a continuous, community-driven process. Panvas addresses these systemic failures with a novel combination of economic incentives (paid reviews) and rich interaction mechanisms (multi-dimensional ratings, threaded discussions, and expert-led reviews). By moving beyond the traditional accept/reject paradigm and integrating paper hosting with code/data repositories and social networking, Panvas fosters a meritocratic environment for scholarly communication and presents a radical rethinking of how we evaluate and disseminate scientific knowledge. We present the system design, development roadmap, and a user study plan to evaluate its effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18336v1-abstract-full').style.display = 'none'; document.getElementById('2503.18336v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Work in progress, vision paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18313">arXiv:2503.18313</a> <span> [<a href="https://arxiv.org/pdf/2503.18313">pdf</a>, <a href="https://arxiv.org/format/2503.18313">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> DeepFund: Will LLM be Professional at Fund Investment? A Live Arena Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+C">Changlun Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yao Shi</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yuyu Luo</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+N">Nan Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18313v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision making, particularly in fund investment, remains inadequately evaluated. Current benchmarks primarily assess LLMs understanding of financial documents rather than their ability to manage assets or analyze trading opportunities in dynamic market conditions. A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18313v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18313v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18313v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision making, particularly in fund investment, remains inadequately evaluated. Current benchmarks primarily assess LLMs understanding of financial documents rather than their ability to manage assets or analyze trading opportunities in dynamic market conditions. A critical limitation in existing evaluation methodologies is the backtesting approach, which suffers from information leakage when LLMs are evaluated on historical data they may have encountered during pretraining. This paper introduces DeepFund, a comprehensive platform for evaluating LLM based trading strategies in a simulated live environment. Our approach implements a multi agent framework where LLMs serve as both analysts and managers, creating a realistic simulation of investment decision making. The platform employs a forward testing methodology that mitigates information leakage by evaluating models on market data released after their training cutoff dates. We provide a web interface that visualizes model performance across different market conditions and investment parameters, enabling detailed comparative analysis. Through DeepFund, we aim to provide a more accurate and fair assessment of LLMs capabilities in fund investment, offering insights into their potential real world applications in financial markets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18313v1-abstract-full').style.display = 'none'; document.getElementById('2503.18313v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17984">arXiv:2503.17984</a> <span> [<a href="https://arxiv.org/pdf/2503.17984">pdf</a>, <a href="https://arxiv.org/format/2503.17984">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"> Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+M">Maochen Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zekun Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian Zhang</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+L">Lei Qi</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yinghuan Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.17984v1-abstract-short" style="display: inline;"> Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed, it remains challenging to effectively and accurately utilize unlabeled data. In this paper, we propose a novel framework called Taste More Taste Better (TMTB), which emphasizes both data and model aspects. Firstly, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17984v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17984v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17984v1-abstract-full" style="display: none;"> Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed, it remains challenging to effectively and accurately utilize unlabeled data. In this paper, we propose a novel framework called Taste More Taste Better (TMTB), which emphasizes both data and model aspects. Firstly, we explore a data augmentation technique well-suited for the crowd counting task. By inpainting the background regions, this technique can effectively enhance data diversity while preserving the fidelity of the entire scenes. Secondly, we introduce the Visual State Space Model as backbone to capture the global context information from crowd scenes, which is crucial for extremely crowded, low-light, and adverse weather scenarios. In addition to the traditional regression head for exact prediction, we employ an Anti-Noise classification head to provide less exact but more accurate supervision, since the regression head is sensitive to noise in manual annotations. We conduct extensive experiments on four benchmark datasets and show that our method outperforms state-of-the-art methods by a large margin. Code is publicly available on https://github.com/syhien/taste_more_taste_better. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17984v1-abstract-full').style.display = 'none'; document.getElementById('2503.17984v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by CVPR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17784">arXiv:2503.17784</a> <span> [<a href="https://arxiv.org/pdf/2503.17784">pdf</a>, <a href="https://arxiv.org/format/2503.17784">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> MEPNet: Medical Entity-balanced Prompting Network for Brain CT Report Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaodan Zhang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yanzhao Shi</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+J">Junzhong Ji</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+C">Chengxin Zheng</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+L">Liangqiong Qu</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="2503.17784v1-abstract-short" style="display: inline;"> The automatic generation of brain CT reports has gained widespread attention, given its potential to assist radiologists in diagnosing cranial diseases. However, brain CT scans involve extensive medical entities, such as diverse anatomy regions and lesions, exhibiting highly inconsistent spatial patterns in 3D volumetric space. This leads to biased learning of medical entities in existing methods,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17784v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17784v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17784v1-abstract-full" style="display: none;"> The automatic generation of brain CT reports has gained widespread attention, given its potential to assist radiologists in diagnosing cranial diseases. However, brain CT scans involve extensive medical entities, such as diverse anatomy regions and lesions, exhibiting highly inconsistent spatial patterns in 3D volumetric space. This leads to biased learning of medical entities in existing methods, resulting in repetitiveness and inaccuracy in generated reports. To this end, we propose a Medical Entity-balanced Prompting Network (MEPNet), which harnesses the large language model (LLM) to fairly interpret various entities for accurate brain CT report generation. By introducing the visual embedding and the learning status of medical entities as enriched clues, our method prompts the LLM to balance the learning of diverse entities, thereby enhancing reports with comprehensive findings. First, to extract visual embedding of entities, we propose Knowledge-driven Joint Attention to explore and distill entity patterns using both explicit and implicit medical knowledge. Then, a Learning Status Scorer is designed to evaluate the learning of entity visual embeddings, resulting in unique learning status for individual entities. Finally, these entity visual embeddings and status are elaborately integrated into multi-modal prompts, to guide the text generation of LLM. This process allows LLM to self-adapt the learning process for biased-fitted entities, thereby covering detailed findings in generated reports. We conduct experiments on two brain CT report generation benchmarks, showing the effectiveness in clinical accuracy and text coherence. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17784v1-abstract-full').style.display = 'none'; document.getElementById('2503.17784v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">AAAI 2025 Oral Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17069">arXiv:2503.17069</a> <span> [<a href="https://arxiv.org/pdf/2503.17069">pdf</a>, <a href="https://arxiv.org/format/2503.17069">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"> PVChat: Personalized Video Chat with One-Shot Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yufei Shi</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+W">Weilong Yan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+G">Gang Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yumeng Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuchen Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenxi Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+F+R">Fei Richard Yu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Ming Li</a>, <a href="/search/cs?searchtype=author&query=Yeo%2C+S+Y">Si Yong Yeo</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="2503.17069v1-abstract-short" style="display: inline;"> Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as "Wilson is receiving chemotherapy" or "Tom is discussing with Sarah", limiting their applicability in smart healthcare and smart home environments. To address this limitation, we propose a one-shot learning framewor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17069v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17069v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17069v1-abstract-full" style="display: none;"> Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as "Wilson is receiving chemotherapy" or "Tom is discussing with Sarah", limiting their applicability in smart healthcare and smart home environments. To address this limitation, we propose a one-shot learning framework PVChat, the first personalized ViLLM that enables subject-aware question answering (QA) from a single video for each subject. Our approach optimizes a Mixture-of-Heads (MoH) enhanced ViLLM on a synthetically augmented video-QA dataset, leveraging a progressive image-to-video learning strategy. Specifically, we introduce an automated augmentation pipeline that synthesizes identity-preserving positive samples and retrieves hard negatives from existing video corpora, generating a diverse training dataset with four QA types: existence, appearance, action, and location inquiries. To enhance subject-specific learning, we propose a ReLU Routing MoH attention mechanism, alongside two novel objectives: (1) Smooth Proximity Regularization for progressive learning through exponential distance scaling and (2) Head Activation Enhancement for balanced attention routing. Finally, we adopt a two-stage training strategy, transitioning from image pre-training to video fine-tuning, enabling a gradual learning process from static attributes to dynamic representations. We evaluate PVChat on diverse datasets covering medical scenarios, TV series, anime, and real-world footage, demonstrating its superiority in personalized feature understanding after learning from a single video, compared to state-of-the-art ViLLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17069v1-abstract-full').style.display = 'none'; document.getElementById('2503.17069v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.16997">arXiv:2503.16997</a> <span> [<a href="https://arxiv.org/pdf/2503.16997">pdf</a>, <a href="https://arxiv.org/format/2503.16997">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"> Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+Q">Qinghe Ma</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zekun Li</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+L">Lei Qi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Q">Qian Yu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yinghuan Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.16997v1-abstract-short" style="display: inline;"> Large pretrained visual foundation models exhibit impressive general capabilities. However, the extensive prior knowledge inherent in these models can sometimes be a double-edged sword when adapting them to downstream tasks in specific domains. In the context of semi-supervised medical image segmentation with domain shift, foundation models like MedSAM tend to make overconfident predictions, some… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16997v1-abstract-full').style.display = 'inline'; document.getElementById('2503.16997v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16997v1-abstract-full" style="display: none;"> Large pretrained visual foundation models exhibit impressive general capabilities. However, the extensive prior knowledge inherent in these models can sometimes be a double-edged sword when adapting them to downstream tasks in specific domains. In the context of semi-supervised medical image segmentation with domain shift, foundation models like MedSAM tend to make overconfident predictions, some of which are incorrect. The error accumulation hinders the effective utilization of unlabeled data and limits further improvements. In this paper, we introduce a Synergistic training framework for Foundation and Conventional models (SynFoC) to address the issue. We observe that a conventional model trained from scratch has the ability to correct the high-confidence mispredictions of the foundation model, while the foundation model can supervise it with high-quality pseudo-labels in the early training stages. Furthermore, to enhance the collaborative training effectiveness of both models and promote reliable convergence towards optimization, the consensus-divergence consistency regularization is proposed. We demonstrate the superiority of our method across four public multi-domain datasets. In particular, our method improves the Dice score by 10.31\% on the Prostate dataset. Our code is available at https://github.com/MQinghe/SynFoC . <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16997v1-abstract-full').style.display = 'none'; document.getElementById('2503.16997v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by CVPR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.16973">arXiv:2503.16973</a> <span> [<a href="https://arxiv.org/pdf/2503.16973">pdf</a>, <a href="https://arxiv.org/format/2503.16973">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"> ARFlow: Human Action-Reaction Flow Matching with Physical Guidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wentao Jiang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingya Wang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Haotao Lu</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+K">Kaiyang Ji</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+B">Baoxiong Jia</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+S">Siyuan Huang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Ye Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.16973v2-abstract-short" style="display: inline;"> Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising performance, they exhibit two key limitations for interaction synthesis: reliance on complex noise-to-reaction generators with intricate conditional mechanisms,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16973v2-abstract-full').style.display = 'inline'; document.getElementById('2503.16973v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16973v2-abstract-full" style="display: none;"> Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising performance, they exhibit two key limitations for interaction synthesis: reliance on complex noise-to-reaction generators with intricate conditional mechanisms, and frequent physical violations in generated motions. To address these issues, we propose Action-Reaction Flow Matching (ARFlow), a novel framework that establishes direct action-to-reaction mappings, eliminating the need for complex conditional mechanisms. Our approach introduces two key innovations: an x1-prediction method that directly outputs human motions instead of velocity fields, enabling explicit constraint enforcement; and a training-free, gradient-based physical guidance mechanism that effectively prevents body penetration artifacts during sampling. Extensive experiments on NTU120 and Chi3D datasets demonstrate that ARFlow not only outperforms existing methods in terms of Fr茅chet Inception Distance and motion diversity but also significantly reduces body collisions, as measured by our new Intersection Volume and Intersection Frequency metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16973v2-abstract-full').style.display = 'none'; document.getElementById('2503.16973v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project Page: https://arflow2025.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/2503.15949">arXiv:2503.15949</a> <span> [<a href="https://arxiv.org/pdf/2503.15949">pdf</a>, <a href="https://arxiv.org/format/2503.15949">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"> CausalCLIPSeg: Unlocking CLIP's Potential in Referring Medical Image Segmentation with Causal Intervention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yaxiong Chen</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+M">Minghong Wei</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+S">Shengwu Xiong</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.15949v1-abstract-short" style="display: inline;"> Referring medical image segmentation targets delineating lesions indicated by textual descriptions. Aligning visual and textual cues is challenging due to their distinct data properties. Inspired by large-scale pre-trained vision-language models, we propose CausalCLIPSeg, an end-to-end framework for referring medical image segmentation that leverages CLIP. Despite not being trained on medical data… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15949v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15949v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15949v1-abstract-full" style="display: none;"> Referring medical image segmentation targets delineating lesions indicated by textual descriptions. Aligning visual and textual cues is challenging due to their distinct data properties. Inspired by large-scale pre-trained vision-language models, we propose CausalCLIPSeg, an end-to-end framework for referring medical image segmentation that leverages CLIP. Despite not being trained on medical data, we enforce CLIP's rich semantic space onto the medical domain by a tailored cross-modal decoding method to achieve text-to-pixel alignment. Furthermore, to mitigate confounding bias that may cause the model to learn spurious correlations instead of meaningful causal relationships, CausalCLIPSeg introduces a causal intervention module which self-annotates confounders and excavates causal features from inputs for segmentation judgments. We also devise an adversarial min-max game to optimize causal features while penalizing confounding ones. Extensive experiments demonstrate the state-of-the-art performance of our proposed method. Code is available at https://github.com/WUTCM-Lab/CausalCLIPSeg. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15949v1-abstract-full').style.display = 'none'; document.getElementById('2503.15949v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 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/2503.15940">arXiv:2503.15940</a> <span> [<a href="https://arxiv.org/pdf/2503.15940">pdf</a>, <a href="https://arxiv.org/format/2503.15940">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"> UniCrossAdapter: Multimodal Adaptation of CLIP for Radiology Report Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yaxiong Chen</a>, <a href="/search/cs?searchtype=author&query=Du%2C+C">Chuang Du</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunlei Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+S">Shengwu Xiong</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.15940v1-abstract-short" style="display: inline;"> Automated radiology report generation aims to expedite the tedious and error-prone reporting process for radiologists. While recent works have made progress, learning to align medical images and textual findings remains challenging due to the relative scarcity of labeled medical data. For example, datasets for this task are much smaller than those used for image captioning in computer vision. In t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15940v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15940v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15940v1-abstract-full" style="display: none;"> Automated radiology report generation aims to expedite the tedious and error-prone reporting process for radiologists. While recent works have made progress, learning to align medical images and textual findings remains challenging due to the relative scarcity of labeled medical data. For example, datasets for this task are much smaller than those used for image captioning in computer vision. In this work, we propose to transfer representations from CLIP, a large-scale pre-trained vision-language model, to better capture cross-modal semantics between images and texts. However, directly applying CLIP is suboptimal due to the domain gap between natural images and radiology. To enable efficient adaptation, we introduce UniCrossAdapter, lightweight adapter modules that are incorporated into CLIP and fine-tuned on the target task while keeping base parameters fixed. The adapters are distributed across modalities and their interaction to enhance vision-language alignment. Experiments on two public datasets demonstrate the effectiveness of our approach, advancing state-of-the-art in radiology report generation. The proposed transfer learning framework provides a means of harnessing semantic knowledge from large-scale pre-trained models to tackle data-scarce medical vision-language tasks. Code is available at https://github.com/chauncey-tow/MRG-CLIP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15940v1-abstract-full').style.display = 'none'; document.getElementById('2503.15940v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 2024 Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15936">arXiv:2503.15936</a> <span> [<a href="https://arxiv.org/pdf/2503.15936">pdf</a>, <a href="https://arxiv.org/format/2503.15936">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> No More Head-Turning: Exploring Passthrough Techniques for Addressing Rear Interruptions from the Front in VR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Zixuan Guo</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuekai Shi</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+T">Tiantian Ye</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+T">Tingjie Wan</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+H">Hai-Ning Liang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.15936v1-abstract-short" style="display: inline;"> Virtual reality (VR) users often encounter interruptions, posing challenges to maintaining real-world awareness during immersive experiences. The Passthrough feature in VR headsets allows users to view their physical surroundings without removing the headset. However, when interruptions come from the rear, users need to turn their heads to see the real world, which can lead to negative experiences… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15936v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15936v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15936v1-abstract-full" style="display: none;"> Virtual reality (VR) users often encounter interruptions, posing challenges to maintaining real-world awareness during immersive experiences. The Passthrough feature in VR headsets allows users to view their physical surroundings without removing the headset. However, when interruptions come from the rear, users need to turn their heads to see the real world, which can lead to negative experiences in VR. Study 1, conducted through semi-structured interviews involving 13 participants, found that users are less likely to use Passthrough for rear interruptions due to large head-turning movements, which cause inconvenience, increase the risk of motion sickness, and reduce the experience. Building on these findings, we introduced three Passthrough techniques in Study 2 for displaying the rear view in front of the user: Full Rear Passthrough + Pause (FRPP), Rear Passthrough Window (RPW), and Rear Passthrough AR (RPAR). Compared to the Baseline method that requires head-turning, all three systems reduced physical and temporal demands, alleviated disorientation caused by motion sickness, and provided a better user experience for managing rear interruptions. Among these, FRPP and RPAR were the most preferred. These findings provide valuable insights for future VR design, emphasizing the need for solutions that effectively manage rear interruptions while maintaining user comfort and experience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15936v1-abstract-full').style.display = 'none'; document.getElementById('2503.15936v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14979">arXiv:2503.14979</a> <span> [<a href="https://arxiv.org/pdf/2503.14979">pdf</a>, <a href="https://arxiv.org/format/2503.14979">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"> One-Shot Medical Video Object Segmentation via Temporal Contrastive Memory Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yaxiong Chen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Junjian Hu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunlei Li</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+S">Shengwu Xiong</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.14979v1-abstract-short" style="display: inline;"> Video object segmentation is crucial for the efficient analysis of complex medical video data, yet it faces significant challenges in data availability and annotation. We introduce the task of one-shot medical video object segmentation, which requires separating foreground and background pixels throughout a video given only the mask annotation of the first frame. To address this problem, we propos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14979v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14979v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14979v1-abstract-full" style="display: none;"> Video object segmentation is crucial for the efficient analysis of complex medical video data, yet it faces significant challenges in data availability and annotation. We introduce the task of one-shot medical video object segmentation, which requires separating foreground and background pixels throughout a video given only the mask annotation of the first frame. To address this problem, we propose a temporal contrastive memory network comprising image and mask encoders to learn feature representations, a temporal contrastive memory bank that aligns embeddings from adjacent frames while pushing apart distant ones to explicitly model inter-frame relationships and stores these features, and a decoder that fuses encoded image features and memory readouts for segmentation. We also collect a diverse, multi-source medical video dataset spanning various modalities and anatomies to benchmark this task. Extensive experiments demonstrate state-of-the-art performance in segmenting both seen and unseen structures from a single exemplar, showing ability to generalize from scarce labels. This highlights the potential to alleviate annotation burdens for medical video analysis. Code is available at https://github.com/MedAITech/TCMN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14979v1-abstract-full').style.display = 'none'; document.getElementById('2503.14979v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 2024 Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14966">arXiv:2503.14966</a> <span> [<a href="https://arxiv.org/pdf/2503.14966">pdf</a>, <a href="https://arxiv.org/format/2503.14966">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tingxiu Chen</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+B">Bingcong Yan</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.14966v1-abstract-short" style="display: inline;"> Ultrasound video classification enables automated diagnosis and has emerged as an important research area. However, publicly available ultrasound video datasets remain scarce, hindering progress in developing effective video classification models. We propose addressing this shortage by synthesizing plausible ultrasound videos from readily available, abundant ultrasound images. To this end, we intr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14966v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14966v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14966v1-abstract-full" style="display: none;"> Ultrasound video classification enables automated diagnosis and has emerged as an important research area. However, publicly available ultrasound video datasets remain scarce, hindering progress in developing effective video classification models. We propose addressing this shortage by synthesizing plausible ultrasound videos from readily available, abundant ultrasound images. To this end, we introduce a latent dynamic diffusion model (LDDM) to efficiently translate static images to dynamic sequences with realistic video characteristics. We demonstrate strong quantitative results and visually appealing synthesized videos on the BUSV benchmark. Notably, training video classification models on combinations of real and LDDM-synthesized videos substantially improves performance over using real data alone, indicating our method successfully emulates dynamics critical for discrimination. Our image-to-video approach provides an effective data augmentation solution to advance ultrasound video analysis. Code is available at https://github.com/MedAITech/U_I2V. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14966v1-abstract-full').style.display = 'none'; document.getElementById('2503.14966v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 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/2503.14958">arXiv:2503.14958</a> <span> [<a href="https://arxiv.org/pdf/2503.14958">pdf</a>, <a href="https://arxiv.org/format/2503.14958">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"> Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunlei Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.14958v1-abstract-short" style="display: inline;"> Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime that utilizes annotations from only a few video frames and leverages existing labeled images to minimize costly video annotations. Specifically, we propose a two… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14958v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14958v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14958v1-abstract-full" style="display: none;"> Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime that utilizes annotations from only a few video frames and leverages existing labeled images to minimize costly video annotations. Specifically, we propose a two-phase framework. First, we learn a few-shot segmentation model using labeled images. Subsequently, to improve performance without full supervision, we introduce a spatiotemporal consistency relearning approach on medical videos that enforces consistency between consecutive frames. Constraints are also enforced between the image model and relearning model at both feature and prediction levels. Experiments demonstrate the superiority of our approach over state-of-the-art few-shot segmentation methods. Our model bridges the gap between abundant annotated medical images and scarce, sparsely labeled medical videos to achieve strong video segmentation performance in this low data regime. Code is available at https://github.com/MedAITech/RAB. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14958v1-abstract-full').style.display = 'none'; document.getElementById('2503.14958v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 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/2503.13989">arXiv:2503.13989</a> <span> [<a href="https://arxiv.org/pdf/2503.13989">pdf</a>, <a href="https://arxiv.org/format/2503.13989">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"> Rethinking Cell Counting Methods: Decoupling Counting and Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunlei Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.13989v1-abstract-short" style="display: inline;"> Cell counting in microscopy images is vital in medicine and biology but extremely tedious and time-consuming to perform manually. While automated methods have advanced in recent years, state-of-the-art approaches tend to increasingly complex model designs. In this paper, we propose a conceptually simple yet effective decoupled learning scheme for automated cell counting, consisting of separate cou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13989v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13989v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13989v1-abstract-full" style="display: none;"> Cell counting in microscopy images is vital in medicine and biology but extremely tedious and time-consuming to perform manually. While automated methods have advanced in recent years, state-of-the-art approaches tend to increasingly complex model designs. In this paper, we propose a conceptually simple yet effective decoupled learning scheme for automated cell counting, consisting of separate counter and localizer networks. In contrast to jointly learning counting and density map estimation, we show that decoupling these objectives surprisingly improves results. The counter operates on intermediate feature maps rather than pixel space to leverage global context and produce count estimates, while also generating coarse density maps. The localizer then reconstructs high-resolution density maps that precisely localize individual cells, conditional on the original images and coarse density maps from the counter. Besides, to boost counting accuracy, we further introduce a global message passing module to integrate cross-region patterns. Extensive experiments on four datasets demonstrate that our approach, despite its simplicity, challenges common practice and achieves state-of-the-art performance by significant margins. Our key insight is that decoupled learning alleviates the need to learn counting on high-resolution density maps directly, allowing the model to focus on global features critical for accurate estimates. Code is available at https://github.com/MedAITech/DCL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13989v1-abstract-full').style.display = 'none'; document.getElementById('2503.13989v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 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/2503.13987">arXiv:2503.13987</a> <span> [<a href="https://arxiv.org/pdf/2503.13987">pdf</a>, <a href="https://arxiv.org/format/2503.13987">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Striving for Simplicity: Simple Yet Effective Prior-Aware Pseudo-Labeling for Semi-Supervised Ultrasound Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yaxiong Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yujie Wang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zixuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+S">Shengwu Xiong</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.13987v1-abstract-short" style="display: inline;"> Medical ultrasound imaging is ubiquitous, but manual analysis struggles to keep pace. Automated segmentation can help but requires large labeled datasets, which are scarce. Semi-supervised learning leveraging both unlabeled and limited labeled data is a promising approach. State-of-the-art methods use consistency regularization or pseudo-labeling but grow increasingly complex. Without sufficient l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13987v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13987v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13987v1-abstract-full" style="display: none;"> Medical ultrasound imaging is ubiquitous, but manual analysis struggles to keep pace. Automated segmentation can help but requires large labeled datasets, which are scarce. Semi-supervised learning leveraging both unlabeled and limited labeled data is a promising approach. State-of-the-art methods use consistency regularization or pseudo-labeling but grow increasingly complex. Without sufficient labels, these models often latch onto artifacts or allow anatomically implausible segmentations. In this paper, we present a simple yet effective pseudo-labeling method with an adversarially learned shape prior to regularize segmentations. Specifically, we devise an encoder-twin-decoder network where the shape prior acts as an implicit shape model, penalizing anatomically implausible but not ground-truth-deviating predictions. Without bells and whistles, our simple approach achieves state-of-the-art performance on two benchmarks under different partition protocols. We provide a strong baseline for future semi-supervised medical image segmentation. Code is available at https://github.com/WUTCM-Lab/Shape-Prior-Semi-Seg. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13987v1-abstract-full').style.display = 'none'; document.getElementById('2503.13987v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MICCAI 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/2503.13828">arXiv:2503.13828</a> <span> [<a href="https://arxiv.org/pdf/2503.13828">pdf</a>, <a href="https://arxiv.org/format/2503.13828">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"> Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+C">Chunlei Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jingliang Hu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</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="2503.13828v1-abstract-short" style="display: inline;"> Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approaches leverage generative models like autoencoders and generative adversarial networks (GANs), they often fall short due to overgeneralization. Recent methods explore various strate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13828v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13828v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13828v1-abstract-full" style="display: none;"> Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approaches leverage generative models like autoencoders and generative adversarial networks (GANs), they often fall short due to overgeneralization. Recent methods explore various strategies, including memory banks, normalizing flows, self-supervised learning, and knowledge distillation, to enhance discrimination. Among these, knowledge distillation, particularly reverse distillation, has shown promise. Following this paradigm, we propose a novel scale-aware contrastive reverse distillation model that addresses two key limitations of existing reverse distillation methods: insufficient feature discriminability and inability to handle anomaly scale variations. Specifically, we introduce a contrastive student-teacher learning approach to derive more discriminative representations by generating and exploring out-of-normal distributions. Further, we design a scale adaptation mechanism to softly weight contrastive distillation losses at different scales to account for the scale variation issue. Extensive experiments on benchmark datasets demonstrate state-of-the-art performance, validating the efficacy of the proposed method. Code is available at https://github.com/MedAITech/SCRD4AD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13828v1-abstract-full').style.display = 'none'; document.getElementById('2503.13828v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13756">arXiv:2503.13756</a> <span> [<a href="https://arxiv.org/pdf/2503.13756">pdf</a>, <a href="https://arxiv.org/format/2503.13756">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="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> Fast alignment of heterogeneous images in sliced Wasserstein distance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yunpeng Shi</a>, <a href="/search/cs?searchtype=author&query=Singer%2C+A">Amit Singer</a>, <a href="/search/cs?searchtype=author&query=Verbeke%2C+E+J">Eric J. Verbeke</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="2503.13756v1-abstract-short" style="display: inline;"> Many applications of computer vision rely on the alignment of similar but non-identical images. We present a fast algorithm for aligning heterogeneous images based on optimal transport. Our approach combines the speed of fast Fourier methods with the robustness of sliced probability metrics and allows us to efficiently compute the alignment between two $L \times L$ images using the sliced 2-Wasser… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13756v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13756v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13756v1-abstract-full" style="display: none;"> Many applications of computer vision rely on the alignment of similar but non-identical images. We present a fast algorithm for aligning heterogeneous images based on optimal transport. Our approach combines the speed of fast Fourier methods with the robustness of sliced probability metrics and allows us to efficiently compute the alignment between two $L \times L$ images using the sliced 2-Wasserstein distance in $O(L^2 \log L)$ operations. We show that our method is robust to translations, rotations and deformations in the images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13756v1-abstract-full').style.display = 'none'; document.getElementById('2503.13756v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12946">arXiv:2503.12946</a> <span> [<a href="https://arxiv.org/pdf/2503.12946">pdf</a>, <a href="https://arxiv.org/format/2503.12946">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</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"> Open3DBench: Open-Source Benchmark for 3D-IC Backend Implementation and PPA Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yunqi Shi</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+C">Chengrui Gao</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+W">Wanqi Ren</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Siyuan Xu</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+K">Ke Xue</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+M">Mingxuan Yuan</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+C">Chao Qian</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zhi-Hua Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12946v1-abstract-short" style="display: inline;"> This work introduces Open3DBench, an open-source 3D-IC backend implementation benchmark built upon the OpenROAD-flow-scripts framework, enabling comprehensive evaluation of power, performance, area, and thermal metrics. Our proposed flow supports modular integration of 3D partitioning, placement, 3D routing, RC extraction, and thermal simulation, aligning with advanced 3D flows that rely on commer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12946v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12946v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12946v1-abstract-full" style="display: none;"> This work introduces Open3DBench, an open-source 3D-IC backend implementation benchmark built upon the OpenROAD-flow-scripts framework, enabling comprehensive evaluation of power, performance, area, and thermal metrics. Our proposed flow supports modular integration of 3D partitioning, placement, 3D routing, RC extraction, and thermal simulation, aligning with advanced 3D flows that rely on commercial tools and in-house scripts. We present two foundational 3D placement algorithms: Open3D-Tiling, which emphasizes regular macro placement, and Open3D-DMP, which enhances wirelength optimization through cross-die co-placement with analytical placer DREAMPlace. Experimental results show significant improvements in area (51.19%), wirelength (24.06%), timing (30.84%), and power (5.72%) compared to 2D flows. The results also highlight that better wirelength does not necessarily lead to PPA gain, emphasizing the need of developing PPA-driven methods. Open3DBench offers a standardized, reproducible platform for evaluating 3D EDA methods, effectively bridging the gap between open-source tools and commercial solutions in 3D-IC design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12946v1-abstract-full').style.display = 'none'; document.getElementById('2503.12946v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12609">arXiv:2503.12609</a> <span> [<a href="https://arxiv.org/pdf/2503.12609">pdf</a>, <a href="https://arxiv.org/format/2503.12609">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yitian Shi</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+D">Di Wen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">Guanqi Chen</a>, <a href="/search/cs?searchtype=author&query=Welte%2C+E">Edgar Welte</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sheng Liu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+K">Kunyu Peng</a>, <a href="/search/cs?searchtype=author&query=Stiefelhagen%2C+R">Rainer Stiefelhagen</a>, <a href="/search/cs?searchtype=author&query=Rayyes%2C+R">Rania Rayyes</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="2503.12609v1-abstract-short" style="display: inline;"> We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12609v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12609v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12609v1-abstract-full" style="display: none;"> We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a multi-view uncertainty-driven grasp fusion mechanism that refines grasp confidence and directional uncertainty in real-time, ensuring robust and stable grasp execution. Extensive real-world experiments demonstrate that VISO-Grasp achieves a success rate of $87.5\%$ in target-oriented grasping with the fewest grasp attempts outperforming baselines. To the best of our knowledge, VISO-Grasp is the first unified framework integrating FMs into target-aware active view planning and 6-DoF grasping in environments with severe occlusions and entire invisibility constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12609v1-abstract-full').style.display = 'none'; document.getElementById('2503.12609v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.11674">arXiv:2503.11674</a> <span> [<a href="https://arxiv.org/pdf/2503.11674">pdf</a>, <a href="https://arxiv.org/format/2503.11674">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</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"> Timing-Driven Global Placement by Efficient Critical Path Extraction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yunqi Shi</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Siyuan Xu</a>, <a href="/search/cs?searchtype=author&query=Kai%2C+S">Shixiong Kai</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+X">Xi Lin</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+K">Ke Xue</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+M">Mingxuan Yuan</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+C">Chao Qian</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="2503.11674v1-abstract-short" style="display: inline;"> Timing optimization during the global placement of integrated circuits has been a significant focus for decades, yet it remains a complex, unresolved issue. Recent analytical methods typically use pin-level timing information to adjust net weights, which is fast and simple but neglects the path-based nature of the timing graph. The existing path-based methods, however, cannot balance the accuracy… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11674v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11674v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11674v1-abstract-full" style="display: none;"> Timing optimization during the global placement of integrated circuits has been a significant focus for decades, yet it remains a complex, unresolved issue. Recent analytical methods typically use pin-level timing information to adjust net weights, which is fast and simple but neglects the path-based nature of the timing graph. The existing path-based methods, however, cannot balance the accuracy and efficiency due to the exponential growth of number of critical paths. In this work, we propose a GPU-accelerated timing-driven global placement framework, integrating accurate path-level information into the efficient DREAMPlace infrastructure. It optimizes the fine-grained pin-to-pin attraction objective and is facilitated by efficient critical path extraction. We also design a quadratic distance loss function specifically to align with the RC timing model. Experimental results demonstrate that our method significantly outperforms the current leading timing-driven placers, achieving an average improvement of 40.5% in total negative slack (TNS) and 8.3% in worst negative slack (WNS), as well as an improvement in half-perimeter wirelength (HPWL). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11674v1-abstract-full').style.display = 'none'; document.getElementById('2503.11674v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by DATE'25 as a Best Paper Award</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.10720">arXiv:2503.10720</a> <span> [<a href="https://arxiv.org/pdf/2503.10720">pdf</a>, <a href="https://arxiv.org/format/2503.10720">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"> AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+Y">Yixiong Fang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tianran Sun</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuling Shi</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+X">Xiaodong Gu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.10720v1-abstract-short" style="display: inline;"> While RAG demonstrates remarkable capabilities in LLM applications, its effectiveness is hindered by the ever-increasing length of retrieved contexts, which introduces information redundancy and substantial computational overhead. Existing context pruning methods, such as LLMLingua, lack contextual awareness and offer limited flexibility in controlling compression rates, often resulting in either… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10720v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10720v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10720v1-abstract-full" style="display: none;"> While RAG demonstrates remarkable capabilities in LLM applications, its effectiveness is hindered by the ever-increasing length of retrieved contexts, which introduces information redundancy and substantial computational overhead. Existing context pruning methods, such as LLMLingua, lack contextual awareness and offer limited flexibility in controlling compression rates, often resulting in either insufficient pruning or excessive information loss. In this paper, we propose AttentionRAG, an attention-guided context pruning method for RAG systems. The core idea of AttentionRAG lies in its attention focus mechanism, which reformulates RAG queries into a next-token prediction paradigm. This mechanism isolates the query's semantic focus to a single token, enabling precise and efficient attention calculation between queries and retrieved contexts. Extensive experiments on LongBench and Babilong benchmarks show that AttentionRAG achieves up to 6.3$\times$ context compression while outperforming LLMLingua methods by around 10\% in key metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10720v1-abstract-full').style.display = 'none'; document.getElementById('2503.10720v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.09427">arXiv:2503.09427</a> <span> [<a href="https://arxiv.org/pdf/2503.09427">pdf</a>, <a href="https://arxiv.org/format/2503.09427">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 Language Modeling for High-Accuracy Single Cell Transcriptomics Analysis and Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yaorui Shi</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiaqi Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Sihang Li</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Junfeng Fang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiang Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yang 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="2503.09427v1-abstract-short" style="display: inline;"> Pre-trained language models (PLMs) have revolutionized scientific research, yet their application to single-cell analysis remains limited. Text PLMs cannot process single-cell RNA sequencing data, while cell PLMs lack the ability to handle free text, restricting their use in multimodal tasks. Existing efforts to bridge these modalities often suffer from information loss or inadequate single-modal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09427v1-abstract-full').style.display = 'inline'; document.getElementById('2503.09427v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09427v1-abstract-full" style="display: none;"> Pre-trained language models (PLMs) have revolutionized scientific research, yet their application to single-cell analysis remains limited. Text PLMs cannot process single-cell RNA sequencing data, while cell PLMs lack the ability to handle free text, restricting their use in multimodal tasks. Existing efforts to bridge these modalities often suffer from information loss or inadequate single-modal pre-training, leading to suboptimal performances. To address these challenges, we propose Single-Cell MultiModal Generative Pre-trained Transformer (scMMGPT), a unified PLM for joint cell and text modeling. scMMGPT effectively integrates the state-of-the-art cell and text PLMs, facilitating cross-modal knowledge sharing for improved performance. To bridge the text-cell modality gap, scMMGPT leverages dedicated cross-modal projectors, and undergoes extensive pre-training on 27 million cells -- the largest dataset for multimodal cell-text PLMs to date. This large-scale pre-training enables scMMGPT to excel in joint cell-text tasks, achieving an 84\% relative improvement of textual discrepancy for cell description generation, 20.5\% higher accuracy for cell type annotation, and 4\% improvement in $k$-NN accuracy for text-conditioned pseudo-cell generation, outperforming baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09427v1-abstract-full').style.display = 'none'; document.getElementById('2503.09427v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.09387">arXiv:2503.09387</a> <span> [<a href="https://arxiv.org/pdf/2503.09387">pdf</a>, <a href="https://arxiv.org/format/2503.09387">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"> VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruanjun Li</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Y">Yuedong Tan</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuanming Shi</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+J">Jiawei Shao</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="2503.09387v2-abstract-short" style="display: inline;"> This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate responses. A longstanding challenge in video understanding--particularly for long-term or real-time applications--stems from the substantial computational overhead ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09387v2-abstract-full').style.display = 'inline'; document.getElementById('2503.09387v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09387v2-abstract-full" style="display: none;"> This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate responses. A longstanding challenge in video understanding--particularly for long-term or real-time applications--stems from the substantial computational overhead caused by the extensive length of visual tokens. To address this, VideoScan employs a single semantic carrier token to represent each frame, progressively reducing computational and memory overhead during its two-phase inference process: prefilling and decoding. The embedding of the semantic carrier token is derived from an optimized aggregation of frame-level visual features, ensuring compact yet semantically rich representations. Critically, the corresponding key-value pairs are trained to retain contextual semantics from prior frames, enabling efficient memory management without sacrificing temporal coherence. During inference, the visual tokens of each frame are processed only once during the prefilling phase and subsequently discarded in the decoding stage, eliminating redundant computations. This design ensures efficient VLM inference even under stringent real-time constraints. Comprehensive experiments on diverse offline and online benchmarks demonstrate that LLaVA-Video, supported by our method, achieves up to $\sim 5\times$ and $1.29\times$ speedups compared to its original version and previous efficient streaming video understanding approaches, respectively. Crucially, these improvements are attained while maintaining competitive performance and ensuring stable GPU memory consumption (consistently $\sim 18$GB, independent of video duration). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09387v2-abstract-full').style.display = 'none'; document.getElementById('2503.09387v2-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.09348">arXiv:2503.09348</a> <span> [<a href="https://arxiv.org/pdf/2503.09348">pdf</a>, <a href="https://arxiv.org/format/2503.09348">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"> MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+Z">Zhoutong Ye</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+M">Mingze Sun</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+H">Huan-ang Gao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+C">Chun Yu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuanchun Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.09348v1-abstract-short" style="display: inline;"> Large multimodal models (LMMs) have demonstrated significant potential as generalists in vision-language (VL) tasks. However, there remains a significant gap between state-of-the-art LMMs and human performance when it comes to complex tasks that require a combination of fundamental VL capabilities, as well as tasks involving the grounding of complex instructions. To thoroughly investigate the huma… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09348v1-abstract-full').style.display = 'inline'; document.getElementById('2503.09348v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09348v1-abstract-full" style="display: none;"> Large multimodal models (LMMs) have demonstrated significant potential as generalists in vision-language (VL) tasks. However, there remains a significant gap between state-of-the-art LMMs and human performance when it comes to complex tasks that require a combination of fundamental VL capabilities, as well as tasks involving the grounding of complex instructions. To thoroughly investigate the human-LMM gap and its underlying causes, we propose MOAT, a diverse benchmark with complex real-world VL tasks that are challenging for LMMs. Specifically, the tasks in MOAT require LMMs to engage in generalist problem solving by integrating fundamental VL capabilities such as reading text, counting, understanding spatial relations, grounding textual and visual instructions, etc. All these abilities fit into a taxonomy proposed by us that contains 10 fundamental VL capabilities, enabling MOAT to provide a fine-grained view of LMMs' strengths and weaknesses. Besides, MOAT is the first benchmark to explicitly evaluate LMMs' ability to ground complex text and visual instructions, which is essential to many real-world applications. We evaluate over 20 proprietary and open source LMMs, as well as humans, on MOAT, and found that humans achieved 82.7% accuracy while the best performing LMM (OpenAI o1) achieved only 38.8%. To guide future model development, we analyze common trends in our results and discuss the underlying causes of observed performance gaps between LMMs and humans, focusing on which VL capability forms the bottleneck in complex tasks, whether test time scaling improves performance on MOAT, and how tiling harms LMMs' capability to count. Code and data are available at https://cambrian-yzt.github.io/MOAT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09348v1-abstract-full').style.display = 'none'; document.getElementById('2503.09348v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project page: https://cambrian-yzt.github.io/MOAT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.09046">arXiv:2503.09046</a> <span> [<a href="https://arxiv.org/pdf/2503.09046">pdf</a>, <a href="https://arxiv.org/format/2503.09046">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"> Discovering Influential Neuron Path in Vision Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yifei Liu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yingdong Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Changming Li</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+A">Anqi Pang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sibei Yang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jingyi Yu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+K">Kan 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="2503.09046v1-abstract-short" style="display: inline;"> Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted to demystify these models through input attribution and neuron role analysis, there's been a notable gap in considering layer-level information and the holistic path of information flow across layers. In this paper, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09046v1-abstract-full').style.display = 'inline'; document.getElementById('2503.09046v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09046v1-abstract-full" style="display: none;"> Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted to demystify these models through input attribution and neuron role analysis, there's been a notable gap in considering layer-level information and the holistic path of information flow across layers. In this paper, we investigate the significance of influential neuron paths within vision Transformers, which is a path of neurons from the model input to output that impacts the model inference most significantly. We first propose a joint influence measure to assess the contribution of a set of neurons to the model outcome. And we further provide a layer-progressive neuron locating approach that efficiently selects the most influential neuron at each layer trying to discover the crucial neuron path from input to output within the target model. Our experiments demonstrate the superiority of our method finding the most influential neuron path along which the information flows, over the existing baseline solutions. Additionally, the neuron paths have illustrated that vision Transformers exhibit some specific inner working mechanism for processing the visual information within the same image category. We further analyze the key effects of these neurons on the image classification task, showcasing that the found neuron paths have already preserved the model capability on downstream tasks, which may also shed some lights on real-world applications like model pruning. The project website including implementation code is available at https://foundation-model-research.github.io/NeuronPath/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09046v1-abstract-full').style.display = 'none'; document.getElementById('2503.09046v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in ICLR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.08525">arXiv:2503.08525</a> <span> [<a href="https://arxiv.org/pdf/2503.08525">pdf</a>, <a href="https://arxiv.org/format/2503.08525">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"> GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tong Wei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yijun Yang</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+J">Junliang Xing</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuanchun Shi</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Zongqing Lu</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+D">Deheng Ye</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="2503.08525v1-abstract-short" style="display: inline;"> Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed action reasoning in visual environments is less established. This work investigates this problem through extensive experiments on complex card games, such as 24 po… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08525v1-abstract-full').style.display = 'inline'; document.getElementById('2503.08525v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.08525v1-abstract-full" style="display: none;"> Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed action reasoning in visual environments is less established. This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld. We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse, characterized by a rapid loss of diversity in the agent's thoughts, state-irrelevant and incomplete reasoning, and subsequent invalid actions, resulting in negative rewards. To counteract thought collapse, we highlight the necessity of process guidance and propose an automated corrector that evaluates and refines the agent's reasoning at each RL step. This simple and scalable GTR (Guided Thought Reinforcement) framework trains reasoning and action simultaneously without the need for dense, per-step human labeling. Our experiments demonstrate that GTR significantly enhances the performance and generalization of the LLaVA-7b model across various visual environments, achieving 3-5 times higher task success rates compared to SoTA models with notably smaller model sizes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08525v1-abstract-full').style.display = 'none'; document.getElementById('2503.08525v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.08162">arXiv:2503.08162</a> <span> [<a href="https://arxiv.org/pdf/2503.08162">pdf</a>, <a href="https://arxiv.org/format/2503.08162">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qian%2C+K">Kangan Qian</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Ziang Luo</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+S">Sicong Jiang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zilin Huang</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+J">Jinyu Miao</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Z">Zhikun Ma</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tianze Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiayin Li</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yangfan He</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Z">Zheng Fu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yining Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Boyue Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hezhe Lin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Ziyu Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jiangbo Yu</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+X">Xinyu Jiao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Mengmeng Yang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+K">Kun Jiang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Diange 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="2503.08162v1-abstract-short" style="display: inline;"> Ensuring safe, comfortable, and efficient planning is crucial for autonomous driving systems. While end-to-end models trained on large datasets perform well in standard driving scenarios, they struggle with complex low-frequency events. Recent Large Language Models (LLMs) and Vision Language Models (VLMs) advancements offer enhanced reasoning but suffer from computational inefficiency. Inspired by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08162v1-abstract-full').style.display = 'inline'; document.getElementById('2503.08162v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.08162v1-abstract-full" style="display: none;"> Ensuring safe, comfortable, and efficient planning is crucial for autonomous driving systems. While end-to-end models trained on large datasets perform well in standard driving scenarios, they struggle with complex low-frequency events. Recent Large Language Models (LLMs) and Vision Language Models (VLMs) advancements offer enhanced reasoning but suffer from computational inefficiency. Inspired by the dual-process cognitive model "Thinking, Fast and Slow", we propose $\textbf{FASIONAD}$ -- a novel dual-system framework that synergizes a fast end-to-end planner with a VLM-based reasoning module. The fast system leverages end-to-end learning to achieve real-time trajectory generation in common scenarios, while the slow system activates through uncertainty estimation to perform contextual analysis and complex scenario resolution. Our architecture introduces three key innovations: (1) A dynamic switching mechanism enabling slow system intervention based on real-time uncertainty assessment; (2) An information bottleneck with high-level plan feedback that optimizes the slow system's guidance capability; (3) A bidirectional knowledge exchange where visual prompts enhance the slow system's reasoning while its feedback refines the fast planner's decision-making. To strengthen VLM reasoning, we develop a question-answering mechanism coupled with reward-instruct training strategy. In open-loop experiments, FASIONAD achieves a $6.7\%$ reduction in average $L2$ trajectory error and $28.1\%$ lower collision rate. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08162v1-abstract-full').style.display = 'none'; document.getElementById('2503.08162v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07703">arXiv:2503.07703</a> <span> [<a href="https://arxiv.org/pdf/2503.07703">pdf</a>, <a href="https://arxiv.org/format/2503.07703">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"> Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gong%2C+L">Lixue Gong</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+X">Xiaoxia Hou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Fanshi Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Liang Li</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+X">Xiaochen Lian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+F">Fei Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Liyang Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wei Liu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+W">Wei Lu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yichun Shi</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+S">Shiqi Sun</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Y">Yu Tian</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Z">Zhi Tian</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Peng Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xun Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Ye Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+G">Guofeng Wu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jie Wu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+X">Xin Xia</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+X">Xuefeng Xiao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Linjie Yang</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+Z">Zhonghua Zhai</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuwei Zhang</a> , et al. (3 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="2503.07703v1-abstract-short" style="display: inline;"> Rapid advancement of diffusion models has catalyzed remarkable progress in the field of image generation. However, prevalent models such as Flux, SD3.5 and Midjourney, still grapple with issues like model bias, limited text rendering capabilities, and insufficient understanding of Chinese cultural nuances. To address these limitations, we present Seedream 2.0, a native Chinese-English bilingual im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07703v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07703v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07703v1-abstract-full" style="display: none;"> Rapid advancement of diffusion models has catalyzed remarkable progress in the field of image generation. However, prevalent models such as Flux, SD3.5 and Midjourney, still grapple with issues like model bias, limited text rendering capabilities, and insufficient understanding of Chinese cultural nuances. To address these limitations, we present Seedream 2.0, a native Chinese-English bilingual image generation foundation model that excels across diverse dimensions, which adeptly manages text prompt in both Chinese and English, supporting bilingual image generation and text rendering. We develop a powerful data system that facilitates knowledge integration, and a caption system that balances the accuracy and richness for image description. Particularly, Seedream is integrated with a self-developed bilingual large language model as a text encoder, allowing it to learn native knowledge directly from massive data. This enable it to generate high-fidelity images with accurate cultural nuances and aesthetic expressions described in either Chinese or English. Beside, Glyph-Aligned ByT5 is applied for flexible character-level text rendering, while a Scaled ROPE generalizes well to untrained resolutions. Multi-phase post-training optimizations, including SFT and RLHF iterations, further improve the overall capability. Through extensive experimentation, we demonstrate that Seedream 2.0 achieves state-of-the-art performance across multiple aspects, including prompt-following, aesthetics, text rendering, and structural correctness. Furthermore, Seedream 2.0 has been optimized through multiple RLHF iterations to closely align its output with human preferences, as revealed by its outstanding ELO score. In addition, it can be readily adapted to an instruction-based image editing model, such as SeedEdit, with strong editing capability that balances instruction-following and image consistency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07703v1-abstract-full').style.display = 'none'; document.getElementById('2503.07703v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Official Page: https://team.doubao.com/tech/seedream</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07367">arXiv:2503.07367</a> <span> [<a href="https://arxiv.org/pdf/2503.07367">pdf</a>, <a href="https://arxiv.org/format/2503.07367">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"> LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qian%2C+K">Kangan Qian</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+J">Jinyu Miao</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Ziang Luo</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+Z">Zheng Fu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+a+J">and Jinchen Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yining Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yunlong Wang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+K">Kun Jiang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Mengmeng Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Diange 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="2503.07367v1-abstract-short" style="display: inline;"> Accurate and reliable spatial and motion information plays a pivotal role in autonomous driving systems. However, object-level perception models struggle with handling open scenario categories and lack precise intrinsic geometry. On the other hand, occupancy-based class-agnostic methods excel in representing scenes but fail to ensure physics consistency and ignore the importance of interactions be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07367v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07367v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07367v1-abstract-full" style="display: none;"> Accurate and reliable spatial and motion information plays a pivotal role in autonomous driving systems. However, object-level perception models struggle with handling open scenario categories and lack precise intrinsic geometry. On the other hand, occupancy-based class-agnostic methods excel in representing scenes but fail to ensure physics consistency and ignore the importance of interactions between traffic participants, hindering the model's ability to learn accurate and reliable motion. In this paper, we introduce a novel occupancy-instance modeling framework for class-agnostic motion prediction tasks, named LEGO-Motion, which incorporates instance features into Bird's Eye View (BEV) space. Our model comprises (1) a BEV encoder, (2) an Interaction-Augmented Instance Encoder, and (3) an Instance-Enhanced BEV Encoder, improving both interaction relationships and physics consistency within the model, thereby ensuring a more accurate and robust understanding of the environment. Extensive experiments on the nuScenes dataset demonstrate that our method achieves state-of-the-art performance, outperforming existing approaches. Furthermore, the effectiveness of our framework is validated on the advanced FMCW LiDAR benchmark, showcasing its practical applicability and generalization capabilities. The code will be made publicly available to facilitate further research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07367v1-abstract-full').style.display = 'none'; document.getElementById('2503.07367v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07110">arXiv:2503.07110</a> <span> [<a href="https://arxiv.org/pdf/2503.07110">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</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"> A LSTM-Transformer Model for pulsation control of pVADs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=E%2C+C">Chaoran E</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chenghan Chen</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuyang Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haiyun Wang</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+P">Peixin Hua</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiwen 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="2503.07110v1-abstract-short" style="display: inline;"> Methods: A method of the pulsation for a pVAD is proposed (AP-pVAD Model). AP-pVAD Model consists of two parts: NPQ Model and LSTM-Transformer Model. (1)The NPQ Model determines the mathematical relationship between motor speed, pressure, and flow rate for the pVAD. (2)The Attention module of Transformer neural network is integrated into the LSTM neural network to form the new LSTM-Transformer Mod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07110v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07110v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07110v1-abstract-full" style="display: none;"> Methods: A method of the pulsation for a pVAD is proposed (AP-pVAD Model). AP-pVAD Model consists of two parts: NPQ Model and LSTM-Transformer Model. (1)The NPQ Model determines the mathematical relationship between motor speed, pressure, and flow rate for the pVAD. (2)The Attention module of Transformer neural network is integrated into the LSTM neural network to form the new LSTM-Transformer Model to predict the pulsation time characteristic points for adjusting the motor speed of the pVAD. Results: The AP-pVAD Model is validated in three hydraulic experiments and an animal experiment. (1)The pressure provided by pVAD calculated with the NPQ Model has a maximum error of only 2.15 mmHg compared to the expected values. (2)The pulsation time characteristic points predicted by the LSTM-Transformer Model shows a maximum prediction error of 1.78ms, which is significantly lower than other methods. (3)The in-vivo test of pVAD in animal experiment has significant improvements in aortic pressure. Animals survive for over 27 hours after the initiation of pVAD operation. Conclusion: (1)For a given pVAD, motor speed has a linear relationship with pressure and a quadratic relationship with flow. (2)Deep learning can be used to predict pulsation characteristic time points, with the LSTM-Transformer Model demonstrating minimal prediction error and better robust performance under conditions of limited dataset sizes, elevated noise levels, and diverse hyperparameter combinations, demonstrating its feasibility and effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07110v1-abstract-full').style.display = 'none'; document.getElementById('2503.07110v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07096">arXiv:2503.07096</a> <span> [<a href="https://arxiv.org/pdf/2503.07096">pdf</a>, <a href="https://arxiv.org/format/2503.07096">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jin%2C+Z">Zhao Jin</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+L">Lu Jin</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yizhe Luo</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+S">Shuo Feng</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yucheng Shi</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+K">Kai Zheng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xinde Yu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Mingliang Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.07096v1-abstract-short" style="display: inline;"> Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07096v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07096v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07096v1-abstract-full" style="display: none;"> Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07096v1-abstract-full').style.display = 'none'; document.getElementById('2503.07096v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07020">arXiv:2503.07020</a> <span> [<a href="https://arxiv.org/pdf/2503.07020">pdf</a>, <a href="https://arxiv.org/format/2503.07020">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Combating Partial Perception Deficit in Autonomous Driving with Multimodal LLM Commonsense </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yuting Hu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chenhui Xu</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+R">Ruiyang Qin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+D">Dancheng Liu</a>, <a href="/search/cs?searchtype=author&query=Nassereldine%2C+A">Amir Nassereldine</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yiyu Shi</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Jinjun Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.07020v1-abstract-short" style="display: inline;"> Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Current protocols typically respond with immediate stops or minimal-risk maneuvers, worsening traffic flow and lacking flexibility for rare driving scenarios. In this paper, we propose LLM-RCO, a framework leveraging large language models to integrate human-like driving commonsense into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07020v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07020v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07020v1-abstract-full" style="display: none;"> Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Current protocols typically respond with immediate stops or minimal-risk maneuvers, worsening traffic flow and lacking flexibility for rare driving scenarios. In this paper, we propose LLM-RCO, a framework leveraging large language models to integrate human-like driving commonsense into autonomous systems facing perception deficits. LLM-RCO features four key modules: hazard inference, short-term motion planner, action condition verifier, and safety constraint generator. These modules interact with the dynamic driving environment, enabling proactive and context-aware control actions to override the original control policy of autonomous agents. To improve safety in such challenging conditions, we construct DriveLM-Deficit, a dataset of 53,895 video clips featuring deficits of safety-critical objects, complete with annotations for LLM-based hazard inference and motion planning fine-tuning. Extensive experiments in adverse driving conditions with the CARLA simulator demonstrate that systems equipped with LLM-RCO significantly improve driving performance, highlighting its potential for enhancing autonomous driving resilience against adverse perception deficits. Our results also show that LLMs fine-tuned with DriveLM-Deficit can enable more proactive movements instead of conservative stops in the context of perception deficits. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07020v1-abstract-full').style.display = 'none'; document.getElementById('2503.07020v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.06136">arXiv:2503.06136</a> <span> [<a href="https://arxiv.org/pdf/2503.06136">pdf</a>, <a href="https://arxiv.org/format/2503.06136">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"> GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tao%2C+Y">Ye Tao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiawei Zhang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yahao Shi</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+D">Dongqing Zou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+B">Bin Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.06136v1-abstract-short" style="display: inline;"> Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by dataset scarcity and the absence of strong pre-trained priors, while 2D diffusion-based approaches struggle with geometric consistency. We propose a method that lever… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.06136v1-abstract-full').style.display = 'inline'; document.getElementById('2503.06136v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.06136v1-abstract-full" style="display: none;"> Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by dataset scarcity and the absence of strong pre-trained priors, while 2D diffusion-based approaches struggle with geometric consistency. We propose a method that leverages 2D diffusion models' implicit 3D reasoning ability while ensuring 3D consistency via Gaussian-splatting-based geometric distillation. Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation. Unlike SV3D, which only relies on implicit 2D representations for video generation, Gaussian Splatting explicitly encodes spatial and appearance attributes, enabling multi-view consistency through geometric constraints. These constraints correct view inconsistencies, ensuring robust geometric consistency. As a result, our approach simultaneously generates high-quality, multi-view-consistent images and accurate 3D models, providing a scalable solution for single-image-based 3D generation and bridging the gap between 2D Diffusion diversity and 3D structural coherence. Experimental results demonstrate state-of-the-art multi-view consistency and strong generalization across diverse datasets. The code will be made publicly available upon acceptance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.06136v1-abstract-full').style.display = 'none'; document.getElementById('2503.06136v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.04641">arXiv:2503.04641</a> <span> [<a href="https://arxiv.org/pdf/2503.04641">pdf</a>, <a href="https://arxiv.org/format/2503.04641">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"> Simulating the Real World: A Unified Survey of Multimodal Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yuqi Hu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Longguang Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xian Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Ling-Hao Chen</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Yuwei Guo</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yukai Shi</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Ce Liu</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+A">Anyi Rao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zeyu Wang</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+H">Hui Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.04641v1-abstract-short" style="display: inline;"> Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the physical world, enabling more accurate simulations and meaningful interactions. However, current methods often treat different modalities, including 2D (images… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04641v1-abstract-full').style.display = 'inline'; document.getElementById('2503.04641v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.04641v1-abstract-full" style="display: none;"> Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the physical world, enabling more accurate simulations and meaningful interactions. However, current methods often treat different modalities, including 2D (images), videos, 3D, and 4D representations, as independent domains, overlooking their interdependencies. Additionally, these methods typically focus on isolated dimensions of reality without systematically integrating their connections. In this survey, we present a unified survey for multimodal generative models that investigate the progression of data dimensionality in real-world simulation. Specifically, this survey starts from 2D generation (appearance), then moves to video (appearance+dynamics) and 3D generation (appearance+geometry), and finally culminates in 4D generation that integrate all dimensions. To the best of our knowledge, this is the first attempt to systematically unify the study of 2D, video, 3D and 4D generation within a single framework. To guide future research, we provide a comprehensive review of datasets, evaluation metrics and future directions, and fostering insights for newcomers. This survey serves as a bridge to advance the study of multimodal generative models and real-world simulation within a unified framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04641v1-abstract-full').style.display = 'none'; document.getElementById('2503.04641v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Repository for the related papers at https://github.com/ALEEEHU/World-Simulator</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.04131">arXiv:2503.04131</a> <span> [<a href="https://arxiv.org/pdf/2503.04131">pdf</a>, <a href="https://arxiv.org/format/2503.04131">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jie Liu</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+T">Tiexin Qin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hui Liu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yilei Shi</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+L">Lichao Mou</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X+X">Xiao Xiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shiqi Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoliang 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="2503.04131v1-abstract-short" style="display: inline;"> In this work, we address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment. While Test-time Training (TTT) approaches show promise for this task, they suffer from two significant limitations. Existing TTT works are primarily designed for classification tasks rather than continuous value regression, and they lack mechanisms to handle the quasi-periodic nature… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04131v1-abstract-full').style.display = 'inline'; document.getElementById('2503.04131v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.04131v1-abstract-full" style="display: none;"> In this work, we address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment. While Test-time Training (TTT) approaches show promise for this task, they suffer from two significant limitations. Existing TTT works are primarily designed for classification tasks rather than continuous value regression, and they lack mechanisms to handle the quasi-periodic nature of cardiac signals. To tackle these issues, we propose a novel \textbf{Q}uasi-\textbf{P}eriodic \textbf{A}daptive \textbf{R}egression with \textbf{T}est-time Training (Q-PART) framework. In the training stage, the proposed Quasi-Period Network decomposes the echocardiogram into periodic and aperiodic components within latent space by combining parameterized helix trajectories with Neural Controlled Differential Equations. During inference, our framework further employs a variance minimization strategy across image augmentations that simulate common quality issues in echocardiogram acquisition, along with differential adaptation rates for periodic and aperiodic components. Theoretical analysis is provided to demonstrate that our variance minimization objective effectively bounds the regression error under mild conditions. Furthermore, extensive experiments across three pediatric age groups demonstrate that Q-PART not only significantly outperforms existing approaches in pediatric LVEF prediction, but also exhibits strong clinical screening capability with high mAUROC scores (up to 0.9747) and maintains gender-fair performance across all metrics, validating its robustness and practical utility in pediatric echocardiography analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04131v1-abstract-full').style.display = 'none'; document.getElementById('2503.04131v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to CVPR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.04106">arXiv:2503.04106</a> <span> [<a href="https://arxiv.org/pdf/2503.04106">pdf</a>, <a href="https://arxiv.org/format/2503.04106">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"> WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haoran Wang</a>, <a href="/search/cs?searchtype=author&query=Huai%2C+L">Lian Huai</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenbin Li</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+L">Lei Qi</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xingqun Jiang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yinghuan Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.04106v1-abstract-short" style="display: inline;"> We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus on training an adaptor for fine-tuning a large amount of pixel-wise annotated medical images following a fully supervised manner. In this paper, to reduce the l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04106v1-abstract-full').style.display = 'inline'; document.getElementById('2503.04106v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.04106v1-abstract-full" style="display: none;"> We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus on training an adaptor for fine-tuning a large amount of pixel-wise annotated medical images following a fully supervised manner. In this paper, to reduce the labeling cost, we investigate a novel weakly-supervised SAM-based segmentation model, namely WeakMedSAM. Specifically, our proposed WeakMedSAM contains two modules: 1) to mitigate severe co-occurrence in medical images, a sub-class exploration module is introduced to learn accurate feature representations. 2) to improve the quality of the class activation maps, our prompt affinity mining module utilizes the prompt capability of SAM to obtain an affinity map for random-walk refinement. Our method can be applied to any SAM-like backbone, and we conduct experiments with SAMUS and EfficientSAM. The experimental results on three popularly-used benchmark datasets, i.e., BraTS 2019, AbdomenCT-1K, and MSD Cardiac dataset, show the promising results of our proposed WeakMedSAM. Our code is available at https://github.com/wanghr64/WeakMedSAM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04106v1-abstract-full').style.display = 'none'; document.getElementById('2503.04106v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.04059">arXiv:2503.04059</a> <span> [<a href="https://arxiv.org/pdf/2503.04059">pdf</a>, <a href="https://arxiv.org/format/2503.04059">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"> H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yunxiao Shi</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+H">Hong Cai</a>, <a href="/search/cs?searchtype=author&query=Ansari%2C+A">Amin Ansari</a>, <a href="/search/cs?searchtype=author&query=Porikli%2C+F">Fatih Porikli</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="2503.04059v1-abstract-short" style="display: inline;"> 3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving. Most existing methods, however, are computationally expensive, requiring costly attention-based 2D-3D transformation and 3D feature processing. In this paper, we present a novel 3D occupancy prediction approach, H3O, whi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04059v1-abstract-full').style.display = 'inline'; document.getElementById('2503.04059v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.04059v1-abstract-full" style="display: none;"> 3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving. Most existing methods, however, are computationally expensive, requiring costly attention-based 2D-3D transformation and 3D feature processing. In this paper, we present a novel 3D occupancy prediction approach, H3O, which features highly efficient architecture designs that incur a significantly lower computational cost as compared to the current state-of-the-art methods. In addition, to compensate for the ambiguity in ground-truth 3D occupancy labels, we advocate leveraging auxiliary tasks to complement the direct 3D supervision. In particular, we integrate multi-camera depth estimation, semantic segmentation, and surface normal estimation via differentiable volume rendering, supervised by corresponding 2D labels that introduces rich and heterogeneous supervision signals. We conduct extensive experiments on the Occ3D-nuScenes and SemanticKITTI benchmarks that demonstrate the superiority of our proposed H3O. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04059v1-abstract-full').style.display = 'none'; document.getElementById('2503.04059v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICRA 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.03882">arXiv:2503.03882</a> <span> [<a href="https://arxiv.org/pdf/2503.03882">pdf</a>, <a href="https://arxiv.org/format/2503.03882">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"> IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jiangtong Zhu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhao Yang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yinan Shi</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Jianwu Fang</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+J">Jianru Xue</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="2503.03882v1-abstract-short" style="display: inline;"> Online vector map construction based on visual data can bypass the processes of data collection, post-processing, and manual annotation required by traditional map construction, which significantly enhances map-building efficiency. However, existing work treats the online mapping task as a local range perception task, overlooking the spatial scalability required for map construction. We propose IC… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.03882v1-abstract-full').style.display = 'inline'; document.getElementById('2503.03882v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.03882v1-abstract-full" style="display: none;"> Online vector map construction based on visual data can bypass the processes of data collection, post-processing, and manual annotation required by traditional map construction, which significantly enhances map-building efficiency. However, existing work treats the online mapping task as a local range perception task, overlooking the spatial scalability required for map construction. We propose IC-Mapper, an instance-centric online mapping framework, which comprises two primary components: 1) Instance-centric temporal association module: For the detection queries of adjacent frames, we measure them in both feature and geometric dimensions to obtain the matching correspondence between instances across frames. 2) Instance-centric spatial fusion module: We perform point sampling on the historical global map from a spatial dimension and integrate it with the detection results of instances corresponding to the current frame to achieve real-time expansion and update of the map. Based on the nuScenes dataset, we evaluate our approach on detection, tracking, and global mapping metrics. Experimental results demonstrate the superiority of IC-Mapper against other state-of-the-art methods. Code will be released on https://github.com/Brickzhuantou/IC-Mapper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.03882v1-abstract-full').style.display = 'none'; document.getElementById('2503.03882v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.02398">arXiv:2503.02398</a> <span> [<a href="https://arxiv.org/pdf/2503.02398">pdf</a>, <a href="https://arxiv.org/format/2503.02398">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> </div> </div> <p class="title is-5 mathjax"> PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yunxiao Shi</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+W">Wujiang Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zeqi Zhang</a>, <a href="/search/cs?searchtype=author&query=Zi%2C+X">Xing Zi</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qiang Wu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Min Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.02398v1-abstract-short" style="display: inline;"> Recommendation agents leverage large language models for user modeling LLM UM to construct textual personas guiding alignment with real users. However existing LLM UM methods struggle with long user generated content UGC due to context limitations and performance degradation. To address this sampling strategies prioritize relevance or recency are often applied yet they inevitably neglect the diver… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02398v1-abstract-full').style.display = 'inline'; document.getElementById('2503.02398v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.02398v1-abstract-full" style="display: none;"> Recommendation agents leverage large language models for user modeling LLM UM to construct textual personas guiding alignment with real users. However existing LLM UM methods struggle with long user generated content UGC due to context limitations and performance degradation. To address this sampling strategies prioritize relevance or recency are often applied yet they inevitably neglect the diverse user interests embedded within the discarded behaviors resulting in incomplete modeling and degraded profiling quality. Furthermore relevance based sampling requires real time retrieval forcing the user modeling process to operate online which introduces significant latency overhead. In this paper we propose PersonaX an agent agnostic LLM UM framework that tackles these challenges through sub behavior sequence SBS selection and offline multi persona construction. PersonaX extracts compact SBS segments offline to capture diverse user interests generating fine grained textual personas that are cached for efficient online retrieval. This approach ensures that the user persona used for prompting remains highly relevant to the current context while eliminating the need for online user modeling. For SBS selection we ensure both efficiency length less than five and high representational quality by balancing prototypicality and diversity within the sampled data. Extensive experiments validate the effectiveness and versatility of PersonaX in high quality user profiling. Utilizing only 30 to 50 percent of the behavioral data with a sequence length of 480 integrating PersonaX with AgentCF yields an absolute performance improvement of 3 to 11 percent while integration with Agent4Rec results in a gain of 10 to 50 percent. PersonaX as an agent agnostic framework sets a new benchmark for scalable user modeling paving the way for more accurate and efficient LLM driven recommendation agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02398v1-abstract-full').style.display = 'none'; document.getElementById('2503.02398v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">draft paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.02335">arXiv:2503.02335</a> <span> [<a href="https://arxiv.org/pdf/2503.02335">pdf</a>, <a href="https://arxiv.org/format/2503.02335">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Unlocking a New Rust Programming Experience: Fast and Slow Thinking with LLMs to Conquer Undefined Behaviors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+R">Renshuang Jiang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+P">Pan Dong</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+Z">Zhenling Duan</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yu Shi</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+X">Xiaoxiang Fang</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yan Ding</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+J">Jun Ma</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shuai Zhao</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhe Jiang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.02335v1-abstract-short" style="display: inline;"> To provide flexibility and low-level interaction capabilities, the unsafe tag in Rust is essential in many projects, but undermines memory safety and introduces Undefined Behaviors (UBs) that reduce safety. Eliminating these UBs requires a deep understanding of Rust's safety rules and strong typing. Traditional methods require depth analysis of code, which is laborious and depends on knowledge des… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02335v1-abstract-full').style.display = 'inline'; document.getElementById('2503.02335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.02335v1-abstract-full" style="display: none;"> To provide flexibility and low-level interaction capabilities, the unsafe tag in Rust is essential in many projects, but undermines memory safety and introduces Undefined Behaviors (UBs) that reduce safety. Eliminating these UBs requires a deep understanding of Rust's safety rules and strong typing. Traditional methods require depth analysis of code, which is laborious and depends on knowledge design. The powerful semantic understanding capabilities of LLM offer new opportunities to solve this problem. Although existing large model debugging frameworks excel in semantic tasks, limited by fixed processes and lack adaptive and dynamic adjustment capabilities. Inspired by the dual process theory of decision-making (Fast and Slow Thinking), we present a LLM-based framework called RustBrain that automatically and flexibly minimizes UBs in Rust projects. Fast thinking extracts features to generate solutions, while slow thinking decomposes, verifies, and generalizes them abstractly. To apply verification and generalization results to solution generation, enabling dynamic adjustments and precise outputs, RustBrain integrates two thinking through a feedback mechanism. Experimental results on Miri dataset show a 94.3% pass rate and 80.4% execution rate, improving flexibility and Rust projects safety. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02335v1-abstract-full').style.display = 'none'; document.getElementById('2503.02335v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.01699">arXiv:2503.01699</a> <span> [<a href="https://arxiv.org/pdf/2503.01699">pdf</a>, <a href="https://arxiv.org/format/2503.01699">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Camera Measurement of Blood Oxygen Saturation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiankai Tang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xin Liu</a>, <a href="/search/cs?searchtype=author&query=McDuff%2C+D">Daniel McDuff</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhang Jiang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Hongming Hu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+L">Luxi Zhou</a>, <a href="/search/cs?searchtype=author&query=Nagao%2C+N">Nodoka Nagao</a>, <a href="/search/cs?searchtype=author&query=Suzuki%2C+H">Haruta Suzuki</a>, <a href="/search/cs?searchtype=author&query=Nagahama%2C+Y">Yuki Nagahama</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wei Li</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+L">Linhong Ji</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuanchun Shi</a>, <a href="/search/cs?searchtype=author&query=Nishidate%2C+I">Izumi Nishidate</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuntao 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="2503.01699v1-abstract-short" style="display: inline;"> Blood oxygen saturation (SpO2) is a crucial vital sign routinely monitored in medical settings. Traditional methods require dedicated contact sensors, limiting accessibility and comfort. This study presents a deep learning framework for contactless SpO2 measurement using an off-the-shelf camera, addressing challenges related to lighting variations and skin tone diversity. We conducted two large-sc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.01699v1-abstract-full').style.display = 'inline'; document.getElementById('2503.01699v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.01699v1-abstract-full" style="display: none;"> Blood oxygen saturation (SpO2) is a crucial vital sign routinely monitored in medical settings. Traditional methods require dedicated contact sensors, limiting accessibility and comfort. This study presents a deep learning framework for contactless SpO2 measurement using an off-the-shelf camera, addressing challenges related to lighting variations and skin tone diversity. We conducted two large-scale studies with diverse participants and evaluated our method against traditional signal processing approaches in intra- and inter-dataset scenarios. Our approach demonstrated consistent accuracy across demographic groups, highlighting the feasibility of camera-based SpO2 monitoring as a scalable and non-invasive tool for remote health assessment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.01699v1-abstract-full').style.display = 'none'; document.getElementById('2503.01699v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.00533">arXiv:2503.00533</a> <span> [<a href="https://arxiv.org/pdf/2503.00533">pdf</a>, <a href="https://arxiv.org/format/2503.00533">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <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"> BodyGen: Advancing Towards Efficient Embodiment Co-Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+H">Haofei Lu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhe Wu</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+J">Junliang Xing</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jianshu Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruoyu Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhe Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuanchun Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.00533v1-abstract-short" style="display: inline;"> Embodiment co-design aims to optimize a robot's morphology and control policy simultaneously. While prior work has demonstrated its potential for generating environment-adaptive robots, this field still faces persistent challenges in optimization efficiency due to the (i) combinatorial nature of morphological search spaces and (ii) intricate dependencies between morphology and control. We prove th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.00533v1-abstract-full').style.display = 'inline'; document.getElementById('2503.00533v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.00533v1-abstract-full" style="display: none;"> Embodiment co-design aims to optimize a robot's morphology and control policy simultaneously. While prior work has demonstrated its potential for generating environment-adaptive robots, this field still faces persistent challenges in optimization efficiency due to the (i) combinatorial nature of morphological search spaces and (ii) intricate dependencies between morphology and control. We prove that the ineffective morphology representation and unbalanced reward signals between the design and control stages are key obstacles to efficiency. To advance towards efficient embodiment co-design, we propose BodyGen, which utilizes (1) topology-aware self-attention for both design and control, enabling efficient morphology representation with lightweight model sizes; (2) a temporal credit assignment mechanism that ensures balanced reward signals for optimization. With our findings, Body achieves an average 60.03% performance improvement against state-of-the-art baselines. We provide codes and more results on the website: https://genesisorigin.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.00533v1-abstract-full').style.display = 'none'; document.getElementById('2503.00533v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2025 (Spotlight). Project Page: https://genesisorigin.github.io, Code: https://github.com/GenesisOrigin/BodyGen</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.00530">arXiv:2503.00530</a> <span> [<a href="https://arxiv.org/pdf/2503.00530">pdf</a>, <a href="https://arxiv.org/format/2503.00530">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">stat.ML</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"> Trajectory Inference with Smooth Schr枚dinger Bridges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hong%2C+W">Wanli Hong</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yuliang Shi</a>, <a href="/search/cs?searchtype=author&query=Niles-Weed%2C+J">Jonathan Niles-Weed</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="2503.00530v1-abstract-short" style="display: inline;"> Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schr枚dinger Bridges. Our proposal generalizes prior work by allowing the reference process in the Schr枚dinger Bridge problem to be a smooth Gaussian process, leading to more regular and interpretable trajectories in applications. Though na茂vely smoothing the reference process leads to a computationally int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.00530v1-abstract-full').style.display = 'inline'; document.getElementById('2503.00530v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.00530v1-abstract-full" style="display: none;"> Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schr枚dinger Bridges. Our proposal generalizes prior work by allowing the reference process in the Schr枚dinger Bridge problem to be a smooth Gaussian process, leading to more regular and interpretable trajectories in applications. Though na茂vely smoothing the reference process leads to a computationally intractable problem, we identify a class of processes (including the Mat茅rn processes) for which the resulting Smooth Schr枚dinger Bridge problem can be lifted to a simpler problem on phase space, which can be solved in polynomial time. We develop a practical approximation of this algorithm that outperforms existing methods on numerous simulated and real single-cell RNAseq datasets. The code can be found at https://github.com/WanliHongC/Smooth_SB <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.00530v1-abstract-full').style.display = 'none'; document.getElementById('2503.00530v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </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=Shi%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Shi%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository