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 3,919 results for author: <span class="mathjax">Wu, 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=Wu%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="Wu, 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=Wu%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="Wu, 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=Wu%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%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/2503.21781">arXiv:2503.21781</a> <span> [<a href="https://arxiv.org/pdf/2503.21781">pdf</a>, <a href="https://arxiv.org/format/2503.21781">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"> VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+C">Chi-Pin Huang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yen-Siang Wu</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+H">Hung-Kai Chung</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K">Kai-Po Chang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+F">Fu-En Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y+F">Yu-Chiang Frank 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="2503.21781v1-abstract-short" style="display: inline;"> Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framewor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21781v1-abstract-full').style.display = 'inline'; document.getElementById('2503.21781v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.21781v1-abstract-full" style="display: none;"> Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21781v1-abstract-full').style.display = 'none'; document.getElementById('2503.21781v1-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> <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://jasper0314-huang.github.io/videomage-customization</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.21197">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/2503.21036">arXiv:2503.21036</a> <span> [<a href="https://arxiv.org/pdf/2503.21036">pdf</a>, <a href="https://arxiv.org/format/2503.21036">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"> The Art of Tool Interface Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yunnan Wu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Paul Chen</a>, <a href="/search/cs?searchtype=author&query=Baranwal%2C+D">Deshank Baranwal</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jinlong Zhou</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+J">Jian Yuan</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="2503.21036v1-abstract-short" style="display: inline;"> We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the $蟿$-bench retail dataset, Thinker achieves 82.6\% success rate with GPT-4o (version 2024-06-01) (baseline: 68.3\%), and 81.9\% success rate with Llama-3.1 405B (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21036v1-abstract-full').style.display = 'inline'; document.getElementById('2503.21036v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.21036v1-abstract-full" style="display: none;"> We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the $蟿$-bench retail dataset, Thinker achieves 82.6\% success rate with GPT-4o (version 2024-06-01) (baseline: 68.3\%), and 81.9\% success rate with Llama-3.1 405B (baseline: 49.6\%), without any fine-tuning. Thinker effectively closes the gap in reasoning capabilities between the base models by introducing proper structure. The key features of the Thinker framework are: (1) State-Machine Augmented Generation (SMAG), which represents business logic as state machines and the LLM uses state machines as tools. (2) Delegation of tasks from the main reasoning loop to LLM-powered tools. (3) Adaptive context management. Our prompting-only solution achieves signficant gains, while still maintaining a standard agentic architecture with a ReAct style reasoning loop. The key is to innovate on the tool interface design, as exemplified by SMAG and the LLM-powered tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21036v1-abstract-full').style.display = 'none'; document.getElementById('2503.21036v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20499">arXiv:2503.20499</a> <span> [<a href="https://arxiv.org/pdf/2503.20499">pdf</a>, <a href="https://arxiv.org/format/2503.20499">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hao-Han Guo</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+K">Kun Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi-Chen Wu</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+F">Feng-Long Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20499v1-abstract-short" style="display: inline;"> In this work, we propose a high-quality streaming foundation text-to-speech system, FireRedTTS-1S, upgraded from the streamable version of FireRedTTS. FireRedTTS-1S achieves streaming generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be syn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20499v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20499v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20499v1-abstract-full" style="display: none;"> In this work, we propose a high-quality streaming foundation text-to-speech system, FireRedTTS-1S, upgraded from the streamable version of FireRedTTS. FireRedTTS-1S achieves streaming generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be synthesized from the text via a semantic language model in an auto-regressive manner. Meanwhile, the semantic-to-acoustic decoding module simultaneously translates generated semantic tokens into the speech signal in a streaming way via a super-resolution causal audio codec and a multi-stream acoustic language model. This design enables us to produce high-quality speech audio in zero-shot settings while presenting a real-time generation process with low latency under 150ms. In experiments on zero-shot voice cloning, the objective results validate FireRedTTS-1S as a high-quality foundation model with comparable intelligibility and speaker similarity over industrial baseline systems. Furthermore, the subjective score of FireRedTTS-1S highlights its impressive synthesis performance, achieving comparable quality to the ground-truth recordings. These results validate FireRedTTS-1S as a high-quality streaming foundation TTS system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20499v1-abstract-full').style.display = 'none'; document.getElementById('2503.20499v1-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> </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/2503.20287">arXiv:2503.20287</a> <span> [<a href="https://arxiv.org/pdf/2503.20287">pdf</a>, <a href="https://arxiv.org/format/2503.20287">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"> InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuhui Wu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Liyi Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruibin Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shihao Wang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+C">Chenxi Xie</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lei 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="2503.20287v1-abstract-short" style="display: inline;"> Instruction-based video editing allows effective and interactive editing of videos using only instructions without extra inputs such as masks or attributes. However, collecting high-quality training triplets (source video, edited video, instruction) is a challenging task. Existing datasets mostly consist of low-resolution, short duration, and limited amount of source videos with unsatisfactory edi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20287v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20287v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20287v1-abstract-full" style="display: none;"> Instruction-based video editing allows effective and interactive editing of videos using only instructions without extra inputs such as masks or attributes. However, collecting high-quality training triplets (source video, edited video, instruction) is a challenging task. Existing datasets mostly consist of low-resolution, short duration, and limited amount of source videos with unsatisfactory editing quality, limiting the performance of trained editing models. In this work, we present a high-quality Instruction-based Video Editing dataset with 1M triplets, namely InsViE-1M. We first curate high-resolution and high-quality source videos and images, then design an effective editing-filtering pipeline to construct high-quality editing triplets for model training. For a source video, we generate multiple edited samples of its first frame with different intensities of classifier-free guidance, which are automatically filtered by GPT-4o with carefully crafted guidelines. The edited first frame is propagated to subsequent frames to produce the edited video, followed by another round of filtering for frame quality and motion evaluation. We also generate and filter a variety of video editing triplets from high-quality images. With the InsViE-1M dataset, we propose a multi-stage learning strategy to train our InsViE model, progressively enhancing its instruction following and editing ability. Extensive experiments demonstrate the advantages of our InsViE-1M dataset and the trained model over state-of-the-art works. Codes are available at InsViE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20287v1-abstract-full').style.display = 'none'; document.getElementById('2503.20287v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20248">arXiv:2503.20248</a> <span> [<a href="https://arxiv.org/pdf/2503.20248">pdf</a>, <a href="https://arxiv.org/format/2503.20248">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"> Incremental Object Keypoint Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+M">Mingfu Liang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiahuan Zhou</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+X">Xu Zou</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ying Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20248v1-abstract-short" style="display: inline;"> Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. However, these well-trained models can hardly detect the undefined new keypoints in test time, which largely hinders their feasibility for diverse downstream tasks. To handle this, various solutions are explored but still s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20248v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20248v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20248v1-abstract-full" style="display: none;"> Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. However, these well-trained models can hardly detect the undefined new keypoints in test time, which largely hinders their feasibility for diverse downstream tasks. To handle this, various solutions are explored but still suffer from either limited generalizability or transferability. Therefore, in this paper, we explore a novel keypoint learning paradigm in that we only annotate new keypoints in the new data and incrementally train the model, without retaining any old data, called Incremental object Keypoint Learning (IKL). A two-stage learning scheme as a novel baseline tailored to IKL is developed. In the first Knowledge Association stage, given the data labeled with only new keypoints, an auxiliary KA-Net is trained to automatically associate the old keypoints to these new ones based on their spatial and intrinsic anatomical relations. In the second Mutual Promotion stage, based on a keypoint-oriented spatial distillation loss, we jointly leverage the auxiliary KA-Net and the old model for knowledge consolidation to mutually promote the estimation of all old and new keypoints. Owing to the investigation of the correlations between new and old keypoints, our proposed method can not just effectively mitigate the catastrophic forgetting of old keypoints, but may even further improve the estimation of the old ones and achieve a positive transfer beyond anti-forgetting. Such an observation has been solidly verified by extensive experiments on different keypoint datasets, where our method exhibits superiority in alleviating the forgetting issue and boosting performance while enjoying labeling efficiency even under the low-shot data regime. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20248v1-abstract-full').style.display = 'none'; document.getElementById('2503.20248v1-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">The IEEE/CVF Conference on Computer Vision and Pattern Recognition (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/2503.18665">arXiv:2503.18665</a> <span> [<a href="https://arxiv.org/pdf/2503.18665">pdf</a>, <a href="https://arxiv.org/format/2503.18665">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"> Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miao%2C+B">Bingchen Miao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yang Wu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+M">Minghe Gao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Q">Qifan Yu</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+W">Wendong Bu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenqiao Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunfei Li</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+S">Siliang Tang</a>, <a href="/search/cs?searchtype=author&query=Chua%2C+T">Tat-Seng Chua</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Juncheng 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="2503.18665v1-abstract-short" style="display: inline;"> The development of Generalist Virtual Agents (GVAs) powered by Multimodal Large Language Models (MLLMs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive human annotations. To address these challenges, we propose Similar, a Step-wise Multi-dimensional Generalist Re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18665v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18665v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18665v1-abstract-full" style="display: none;"> The development of Generalist Virtual Agents (GVAs) powered by Multimodal Large Language Models (MLLMs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive human annotations. To address these challenges, we propose Similar, a Step-wise Multi-dimensional Generalist Reward Model, which offers fine-grained signals for agent training and can choose better action for inference-time scaling. Specifically, we begin by systematically defining five dimensions for evaluating agent actions. Building on this framework, we design an MCTS-P algorithm to automatically collect and annotate step-wise, five-dimensional agent execution data. Using this data, we train Similar with the Triple-M strategy. Furthermore, we introduce the first benchmark in the virtual agent domain for step-wise, multi-dimensional reward model training and evaluation, named SRM. This benchmark consists of two components: SRMTrain, which serves as the training set for Similar, and SRMEval, a manually selected test set for evaluating the reward model. Experimental results demonstrate that Similar, through its step-wise, multi-dimensional assessment and synergistic gain, provides GVAs with effective intermediate signals during both training and inference-time scaling. The code is available at https://github.com/Galery23/Similar-v1. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18665v1-abstract-full').style.display = 'none'; document.getElementById('2503.18665v1-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/2503.18312">arXiv:2503.18312</a> <span> [<a href="https://arxiv.org/pdf/2503.18312">pdf</a>, <a href="https://arxiv.org/format/2503.18312">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"> Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jin%2C+J">Jianlong Jin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Chenglong Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruixin Zhang</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+S">Sheng Shang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jianqing Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jingyun Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">ShaoMing Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yang Zhao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+S">Shouhong Ding</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+W">Wei Jia</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yunsheng Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18312v1-abstract-short" style="display: inline;"> Palmprint recognition is significantly limited by the lack of large-scale publicly available datasets. Previous methods have adopted B茅zier curves to simulate the palm creases, which then serve as input for conditional GANs to generate realistic palmprints. However, without employing real data fine-tuning, the performance of the recognition model trained on these synthetic datasets would drastical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18312v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18312v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18312v1-abstract-full" style="display: none;"> Palmprint recognition is significantly limited by the lack of large-scale publicly available datasets. Previous methods have adopted B茅zier curves to simulate the palm creases, which then serve as input for conditional GANs to generate realistic palmprints. However, without employing real data fine-tuning, the performance of the recognition model trained on these synthetic datasets would drastically decline, indicating a large gap between generated and real palmprints. This is primarily due to the utilization of an inaccurate palm crease representation and challenges in balancing intra-class variation with identity consistency. To address this, we introduce a polynomial-based palm crease representation that provides a new palm crease generation mechanism more closely aligned with the real distribution. We also propose the palm creases conditioned diffusion model with a novel intra-class variation control method. By applying our proposed $K$-step noise-sharing sampling, we are able to synthesize palmprint datasets with large intra-class variation and high identity consistency. Experimental results show that, for the first time, recognition models trained solely on our synthetic datasets, without any fine-tuning, outperform those trained on real datasets. Furthermore, our approach achieves superior recognition performance as the number of generated identities increases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18312v1-abstract-full').style.display = 'none'; document.getElementById('2503.18312v1-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 CVPR2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17511">arXiv:2503.17511</a> <span> [<a href="https://arxiv.org/pdf/2503.17511">pdf</a>, <a href="https://arxiv.org/format/2503.17511">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"> NAVIUS: Navigated Augmented Reality Visualization for Ureteroscopic Surgery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Acar%2C+A">Ayberk Acar</a>, <a href="/search/cs?searchtype=author&query=Atoum%2C+J">Jumanh Atoum</a>, <a href="/search/cs?searchtype=author&query=Connor%2C+P+S">Peter S. Connor</a>, <a href="/search/cs?searchtype=author&query=Pierre%2C+C">Clifford Pierre</a>, <a href="/search/cs?searchtype=author&query=Lynch%2C+C+N">Carisa N. Lynch</a>, <a href="/search/cs?searchtype=author&query=Kavoussi%2C+N+L">Nicholas L. Kavoussi</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J+Y">Jie Ying Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.17511v1-abstract-short" style="display: inline;"> Ureteroscopy is the standard of care for diagnosing and treating kidney stones and tumors. However, current ureteroscopes have a limited field of view, requiring significant experience to adequately navigate the renal collecting system. This is evidenced by the fact that inexperienced surgeons have higher rates of missed stones. One-third of patients with residual stones require re-operation withi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17511v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17511v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17511v1-abstract-full" style="display: none;"> Ureteroscopy is the standard of care for diagnosing and treating kidney stones and tumors. However, current ureteroscopes have a limited field of view, requiring significant experience to adequately navigate the renal collecting system. This is evidenced by the fact that inexperienced surgeons have higher rates of missed stones. One-third of patients with residual stones require re-operation within 20 months. In order to aid surgeons to fully explore the kidney, this study presents the Navigated Augmented Reality Visualization for Ureteroscopic Surgery (NAVIUS) system. NAVIUS assists surgeons by providing 3D maps of the target anatomy, real-time scope positions, and preoperative imaging overlays. To enable real-time navigation and visualization, we integrate an electromagnetic tracker-based navigation pipeline with augmented reality visualizations. NAVIUS connects to 3D Slicer and Unity with OpenIGTLink, and uses HoloLens 2 as a holographic interface. We evaluate NAVIUS through a user study where surgeons conducted ureteroscopy on kidney phantoms with and without visual guidance. With our proposed system, we observed that surgeons explored more areas within the collecting system with NAVIUS (average 23.73% increase), and NASA-TLX metrics were improved (up to 27.27%). NAVIUS acts as a step towards better surgical outcomes and surgeons' experience. The codebase for the system will be available at: https://github.com/vu-maple-lab/NAVIUS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17511v1-abstract-full').style.display = 'none'; document.getElementById('2503.17511v1-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">11 pages, 5 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17394">arXiv:2503.17394</a> <span> [<a href="https://arxiv.org/pdf/2503.17394">pdf</a>, <a href="https://arxiv.org/format/2503.17394">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Du%2C+K">Kangrui Du</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuhang Wu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+S">Shikuang Deng</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+S">Shi 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="2503.17394v1-abstract-short" style="display: inline;"> Spiking Neural Networks (SNNs), models inspired by neural mechanisms in the brain, allow for energy-efficient implementation on neuromorphic hardware. However, SNNs trained with current direct training approaches are constrained to a specific time step. This "temporal inflexibility" 1) hinders SNNs' deployment on time-step-free fully event-driven chips and 2) prevents energy-performance balance ba… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17394v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17394v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17394v1-abstract-full" style="display: none;"> Spiking Neural Networks (SNNs), models inspired by neural mechanisms in the brain, allow for energy-efficient implementation on neuromorphic hardware. However, SNNs trained with current direct training approaches are constrained to a specific time step. This "temporal inflexibility" 1) hinders SNNs' deployment on time-step-free fully event-driven chips and 2) prevents energy-performance balance based on dynamic inference time steps. In this study, we first explore the feasibility of training SNNs that generalize across different time steps. We then introduce Mixed Time-step Training (MTT), a novel method that improves the temporal flexibility of SNNs, making SNNs adaptive to diverse temporal structures. During each iteration of MTT, random time steps are assigned to different SNN stages, with spikes transmitted between stages via communication modules. After training, the weights are deployed and evaluated on both time-stepped and fully event-driven platforms. Experimental results show that models trained by MTT gain remarkable temporal flexibility, friendliness for both event-driven and clock-driven deployment (nearly lossless on N-MNIST and 10.1% higher than standard methods on CIFAR10-DVS), enhanced network generalization, and near SOTA performance. To the best of our knowledge, this is the first work to report the results of large-scale SNN deployment on fully event-driven scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17394v1-abstract-full').style.display = 'none'; document.getElementById('2503.17394v1-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">20 pages, 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/2503.17088">arXiv:2503.17088</a> <span> [<a href="https://arxiv.org/pdf/2503.17088">pdf</a>, <a href="https://arxiv.org/ps/2503.17088">ps</a>, <a href="https://arxiv.org/format/2503.17088">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Unsourced Random Access in MIMO Quasi-Static Rayleigh Fading Channels: Finite Blocklength and Scaling Law Analyses </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+J">Junyuan Gao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yongpeng Wu</a>, <a href="/search/cs?searchtype=author&query=Caire%2C+G">Giuseppe Caire</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+W">Wei Yang</a>, <a href="/search/cs?searchtype=author&query=Poor%2C+H+V">H. Vincent Poor</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenjun 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="2503.17088v1-abstract-short" style="display: inline;"> This paper considers the unsourced random access (URA) problem with a random and unknown number of active users in multiple-input multiple-output (MIMO) quasi-static Rayleigh fading channels. We derive non-asymptotic achievability bounds on the probability of incorrectly estimating the number of active users, and provide scaling laws on the gap between the estimated and true numbers of active user… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17088v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17088v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17088v1-abstract-full" style="display: none;"> This paper considers the unsourced random access (URA) problem with a random and unknown number of active users in multiple-input multiple-output (MIMO) quasi-static Rayleigh fading channels. We derive non-asymptotic achievability bounds on the probability of incorrectly estimating the number of active users, and provide scaling laws on the gap between the estimated and true numbers of active users. We prove that the error probability reaches a plateau as the power $P$ and blocklength $n$ increase, whereas it decays exponentially with the number $L$ of receive antennas and eventually vanishes. Then, we explore the fundamental limits of URA by deriving non-asymptotic achievability bounds and converse bounds (including two single-user converse bounds and one multi-user ensemble converse bound) on the minimum energy-per-bit required by each active user to transmit $J$ bits with blocklength $n$ under misdetection and false-alarm constraints. Numerical results show that the extra required energy-per-bit due to the uncertainty in the number ${\rm{K}}_a$ of active users decreases as $L$ and $\mathbb{E}[{\rm{K}}_a]$ increase and the error requirement becomes milder. In the non-asymptotic regime, using codewords distributed on a sphere outperforms Gaussian random coding. Existing schemes are shown to exhibit a large gap to our bounds when the number of active users is large, calling for more advanced schemes that perform energy-efficiently in this case. In the asymptotic regime with $n\to\infty$, we establish scaling laws on the minimum required $P$ and $L$ to reliably support ${\rm{K}}_a$ active users as functions of $n$, which highlight the potential of MIMO in enabling low-cost communication and indicate that it is possible for the minimum required $P$ and $L$ to remain on the same order when the number of active users increases but stays below a threshold. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17088v1-abstract-full').style.display = 'none'; document.getElementById('2503.17088v1-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 IEEE Transactions on Information Theory</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17005">arXiv:2503.17005</a> <span> [<a href="https://arxiv.org/pdf/2503.17005">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Autonomous Exploration-Based Precise Mapping for Mobile Robots through Stepwise and Consistent Motions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Muhua Zhang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+L">Lei Ma</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ying Wu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+K">Kai Shen</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yongkui Sun</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+H">Henry Leung</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="2503.17005v1-abstract-short" style="display: inline;"> This paper presents an autonomous exploration framework. It is designed for indoor ground mobile robots that utilize laser Simultaneous Localization and Mapping (SLAM), ensuring process completeness and precise mapping results. For frontier search, the local-global sampling architecture based on multiple Rapidly Exploring Random Trees (RRTs) is employed. Traversability checks during RRT expansion… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17005v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17005v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17005v1-abstract-full" style="display: none;"> This paper presents an autonomous exploration framework. It is designed for indoor ground mobile robots that utilize laser Simultaneous Localization and Mapping (SLAM), ensuring process completeness and precise mapping results. For frontier search, the local-global sampling architecture based on multiple Rapidly Exploring Random Trees (RRTs) is employed. Traversability checks during RRT expansion and global RRT pruning upon map updates eliminate unreachable frontiers, reducing potential collisions and deadlocks. Adaptive sampling density adjustments, informed by obstacle distribution, enhance exploration coverage potential. For frontier point navigation, a stepwise consistent motion strategy is adopted, wherein the robot strictly drives straight on approximately equidistant line segments in the polyline path and rotates in place at segment junctions. This simplified, decoupled motion pattern improves scan-matching stability and mitigates map drift. For process control, the framework serializes frontier point selection and navigation, avoiding oscillation caused by frequent goal changes in conventional parallelized processes. The waypoint retracing mechanism is introduced to generate repeated observations, triggering loop closure detection and backend optimization in graph-based SLAM, thereby improving map consistency and precision. Experiments in both simulation and real-world scenarios validate the effectiveness of the framework. It achieves improved mapping coverage and precision in more challenging environments compared to baseline 2D exploration algorithms. It also shows robustness in supporting resource-constrained robot platforms and maintaining mapping consistency across various LiDAR field-of-view (FoV) configurations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17005v1-abstract-full').style.display = 'none'; document.getElementById('2503.17005v1-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">8 pages, 11 figures. This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.16942">arXiv:2503.16942</a> <span> [<a href="https://arxiv.org/pdf/2503.16942">pdf</a>, <a href="https://arxiv.org/format/2503.16942">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"> Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fan%2C+Y">Yingying Fan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Q">Quanwei Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kaisiyuan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+H">Hang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yingying Li</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+H">Haocheng Feng</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+E">Errui Ding</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yu Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingdong 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="2503.16942v3-abstract-short" style="display: inline;"> Current digital human studies focusing on lip-syncing and body movement are no longer sufficient to meet the growing industrial demand, while human video generation techniques that support interacting with real-world environments (e.g., objects) have not been well investigated. Despite human hand synthesis already being an intricate problem, generating objects in contact with hands and their inter… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16942v3-abstract-full').style.display = 'inline'; document.getElementById('2503.16942v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16942v3-abstract-full" style="display: none;"> Current digital human studies focusing on lip-syncing and body movement are no longer sufficient to meet the growing industrial demand, while human video generation techniques that support interacting with real-world environments (e.g., objects) have not been well investigated. Despite human hand synthesis already being an intricate problem, generating objects in contact with hands and their interactions presents an even more challenging task, especially when the objects exhibit obvious variations in size and shape. To tackle these issues, we present a novel video Reenactment framework focusing on Human-Object Interaction (HOI) via an adaptive Layout-instructed Diffusion model (Re-HOLD). Our key insight is to employ specialized layout representation for hands and objects, respectively. Such representations enable effective disentanglement of hand modeling and object adaptation to diverse motion sequences. To further improve the generation quality of HOI, we design an interactive textural enhancement module for both hands and objects by introducing two independent memory banks. We also propose a layout adjustment strategy for the cross-object reenactment scenario to adaptively adjust unreasonable layouts caused by diverse object sizes during inference. Comprehensive qualitative and quantitative evaluations demonstrate that our proposed framework significantly outperforms existing methods. Project page: https://fyycs.github.io/Re-HOLD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16942v3-abstract-full').style.display = 'none'; document.getElementById('2503.16942v3-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">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">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/2503.16823">arXiv:2503.16823</a> <span> [<a href="https://arxiv.org/pdf/2503.16823">pdf</a>, <a href="https://arxiv.org/format/2503.16823">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Federated Digital Twin Construction via Distributed Sensing: A Game-Theoretic Online Optimization with Overlapping Coalitions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+R">Ruoyang Chen</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+C">Changyan Yi</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+F">Fuhui Zhou</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuan Wu</a>, <a href="/search/cs?searchtype=author&query=Niyato%2C+D">Dusit Niyato</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="2503.16823v1-abstract-short" style="display: inline;"> In this paper, we propose a novel federated framework for constructing the digital twin (DT) model, referring to a living and self-evolving visualization model empowered by artificial intelligence, enabled by distributed sensing under edge-cloud collaboration. In this framework, the DT model to be built at the cloud is regarded as a global one being split into and integrating from multiple functio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16823v1-abstract-full').style.display = 'inline'; document.getElementById('2503.16823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16823v1-abstract-full" style="display: none;"> In this paper, we propose a novel federated framework for constructing the digital twin (DT) model, referring to a living and self-evolving visualization model empowered by artificial intelligence, enabled by distributed sensing under edge-cloud collaboration. In this framework, the DT model to be built at the cloud is regarded as a global one being split into and integrating from multiple functional components, i.e., partial-DTs, created at various edge servers (ESs) using feature data collected by associated sensors. Considering time-varying DT evolutions and heterogeneities among partial-DTs, we formulate an online problem that jointly and dynamically optimizes partial-DT assignments from the cloud to ESs, ES-sensor associations for partial-DT creation, and as well as computation and communication resource allocations for global-DT integration. The problem aims to maximize the constructed DT's model quality while minimizing all induced costs, including energy consumption and configuration costs, in long runs. To this end, we first transform the original problem into an equivalent hierarchical game with an upper-layer two-sided matching game and a lower-layer overlapping coalition formation game. After analyzing these games in detail, we apply the Gale-Shapley algorithm and particularly develop a switch rules-based overlapping coalition formation algorithm to obtain short-term equilibria of upper-layer and lower-layer subgames, respectively. Then, we design a deep reinforcement learning-based solution, called DMO, to extend the result into a long-term equilibrium of the hierarchical game, thereby producing the solution to the original problem. Simulations show the effectiveness of the introduced framework, and demonstrate the superiority of the proposed solution over counterparts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16823v1-abstract-full').style.display = 'none'; document.getElementById('2503.16823v1-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/2503.16263">arXiv:2503.16263</a> <span> [<a href="https://arxiv.org/pdf/2503.16263">pdf</a>, <a href="https://arxiv.org/format/2503.16263">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> From Monocular Vision to Autonomous Action: Guiding Tumor Resection via 3D Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Acar%2C+A">Ayberk Acar</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+M">Mariana Smith</a>, <a href="/search/cs?searchtype=author&query=Al-Zogbi%2C+L">Lidia Al-Zogbi</a>, <a href="/search/cs?searchtype=author&query=Watts%2C+T">Tanner Watts</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Fangjie Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hao Li</a>, <a href="/search/cs?searchtype=author&query=Yilmaz%2C+N">Nural Yilmaz</a>, <a href="/search/cs?searchtype=author&query=Scheikl%2C+P+M">Paul Maria Scheikl</a>, <a href="/search/cs?searchtype=author&query=d%27Almeida%2C+J+F">Jesse F. d'Almeida</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+S">Susheela Sharma</a>, <a href="/search/cs?searchtype=author&query=Branscombe%2C+L">Lauren Branscombe</a>, <a href="/search/cs?searchtype=author&query=Ertop%2C+T+E">Tayfun Efe Ertop</a>, <a href="/search/cs?searchtype=author&query=Webster%2C+R+J">Robert J. Webster III</a>, <a href="/search/cs?searchtype=author&query=Oguz%2C+I">Ipek Oguz</a>, <a href="/search/cs?searchtype=author&query=Kuntz%2C+A">Alan Kuntz</a>, <a href="/search/cs?searchtype=author&query=Krieger%2C+A">Axel Krieger</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J+Y">Jie Ying Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.16263v1-abstract-short" style="display: inline;"> Surgical automation requires precise guidance and understanding of the scene. Current methods in the literature rely on bulky depth cameras to create maps of the anatomy, however this does not translate well to space-limited clinical applications. Monocular cameras are small and allow minimally invasive surgeries in tight spaces but additional processing is required to generate 3D scene understand… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16263v1-abstract-full').style.display = 'inline'; document.getElementById('2503.16263v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16263v1-abstract-full" style="display: none;"> Surgical automation requires precise guidance and understanding of the scene. Current methods in the literature rely on bulky depth cameras to create maps of the anatomy, however this does not translate well to space-limited clinical applications. Monocular cameras are small and allow minimally invasive surgeries in tight spaces but additional processing is required to generate 3D scene understanding. We propose a 3D mapping pipeline that uses only RGB images to create segmented point clouds of the target anatomy. To ensure the most precise reconstruction, we compare different structure from motion algorithms' performance on mapping the central airway obstructions, and test the pipeline on a downstream task of tumor resection. In several metrics, including post-procedure tissue model evaluation, our pipeline performs comparably to RGB-D cameras and, in some cases, even surpasses their performance. These promising results demonstrate that automation guidance can be achieved in minimally invasive procedures with monocular cameras. This study is a step toward the complete autonomy of surgical robots. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16263v1-abstract-full').style.display = 'none'; document.getElementById('2503.16263v1-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">7 Pages, 8 Figures, 1 Table. This work has been submitted IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15788">arXiv:2503.15788</a> <span> [<a href="https://arxiv.org/pdf/2503.15788">pdf</a>, <a href="https://arxiv.org/format/2503.15788">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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> A two-stage model leveraging friendship network for community evolution prediction in interactive networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yanmei Hu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yihang Wu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+B">Biao Cai</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="2503.15788v1-abstract-short" style="display: inline;"> Interactive networks representing user participation and interactions in specific "events" are highly dynamic, with communities reflecting collective behaviors that evolve over time. Predicting these community evolutions is crucial for forecasting the trajectory of the related "event". Some models for community evolution prediction have been witnessed, but they primarily focused on coarse-grained… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15788v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15788v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15788v1-abstract-full" style="display: none;"> Interactive networks representing user participation and interactions in specific "events" are highly dynamic, with communities reflecting collective behaviors that evolve over time. Predicting these community evolutions is crucial for forecasting the trajectory of the related "event". Some models for community evolution prediction have been witnessed, but they primarily focused on coarse-grained evolution types (e.g., expand, dissolve, merge, split), often neglecting fine-grained evolution extents (e.g., the extent of community expansion). Furthermore, these models typically utilize only one network data (here is interactive network data) for dynamic community featurization, overlooking the more stable friendship network that represents the friendships between people to enrich community representations. To address these limitations, we propose a two-stage model that predicts both the type and extent of community evolution. Our model unifies multi-class classification for evolution type and regression for evolution extent within a single framework and fuses data from both interactive and friendship networks for a comprehensive community featurization. We also introduce a hybrid strategy to differentiate between evolution types that are difficult to distinguish. Experimental results on three datasets show the significant superiority of the proposed model over other models, confirming its efficacy in predicting community evolution in interactive networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15788v1-abstract-full').style.display = 'none'; document.getElementById('2503.15788v1-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">15 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15647">arXiv:2503.15647</a> <span> [<a href="https://arxiv.org/pdf/2503.15647">pdf</a>, <a href="https://arxiv.org/format/2503.15647">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"> Multi-Modal Gesture Recognition from Video and Surgical Tool Pose Information via Motion Invariants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Atoum%2C+J">Jumanh Atoum</a>, <a href="/search/cs?searchtype=author&query=Johnston%2C+G+L+H">Garrison L. H. Johnston</a>, <a href="/search/cs?searchtype=author&query=Simaan%2C+N">Nabil Simaan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J+Y">Jie Ying Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.15647v1-abstract-short" style="display: inline;"> Recognizing surgical gestures in real-time is a stepping stone towards automated activity recognition, skill assessment, intra-operative assistance, and eventually surgical automation. The current robotic surgical systems provide us with rich multi-modal data such as video and kinematics. While some recent works in multi-modal neural networks learn the relationships between vision and kinematics d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15647v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15647v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15647v1-abstract-full" style="display: none;"> Recognizing surgical gestures in real-time is a stepping stone towards automated activity recognition, skill assessment, intra-operative assistance, and eventually surgical automation. The current robotic surgical systems provide us with rich multi-modal data such as video and kinematics. While some recent works in multi-modal neural networks learn the relationships between vision and kinematics data, current approaches treat kinematics information as independent signals, with no underlying relation between tool-tip poses. However, instrument poses are geometrically related, and the underlying geometry can aid neural networks in learning gesture representation. Therefore, we propose combining motion invariant measures (curvature and torsion) with vision and kinematics data using a relational graph network to capture the underlying relations between different data streams. We show that gesture recognition improves when combining invariant signals with tool position, achieving 90.3\% frame-wise accuracy on the JIGSAWS suturing dataset. Our results show that motion invariant signals coupled with position are better representations of gesture motion compared to traditional position and quaternion representations. Our results highlight the need for geometric-aware modeling of kinematics for gesture recognition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15647v1-abstract-full').style.display = 'none'; document.getElementById('2503.15647v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15283">arXiv:2503.15283</a> <span> [<a href="https://arxiv.org/pdf/2503.15283">pdf</a>, <a href="https://arxiv.org/format/2503.15283">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"> TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hsiao%2C+T">Teng-Fang Hsiao</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+B">Bo-Kai Ruan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi-Lun Wu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Tzu-Ling Lin</a>, <a href="/search/cs?searchtype=author&query=Shuai%2C+H">Hong-Han Shuai</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="2503.15283v1-abstract-short" style="display: inline;"> Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15283v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15283v1-abstract-full" style="display: none;"> Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point out that textual tokens can implicitly learn visual information from vision tokens. We enhance this interaction by extracting a condensed visual representation from reference images, facilitating selective information sharing through Reference Contextual Masking -- this technique confines the usage of contextual tokens to instruction-relevant visual information. Additionally, our Winner-Takes-All module mitigates distribution shifts by prioritizing the most pertinent references for each vision token. Addressing the gap in TI2I evaluation, we also introduce the FG-TI2I Bench, a comprehensive benchmark tailored for TI2I and compatible with existing T2I methods. Our approach shows robust performance across various benchmarks, confirming its effectiveness in handling complex image-generation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15283v1-abstract-full').style.display = 'none'; document.getElementById('2503.15283v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15079">arXiv:2503.15079</a> <span> [<a href="https://arxiv.org/pdf/2503.15079">pdf</a>, <a href="https://arxiv.org/format/2503.15079">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Ke Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenxi Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chong Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chi Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">YaChen Wu</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+Z">Zhenchang Xing</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qingshan Li</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+X">Xin Peng</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="2503.15079v1-abstract-short" style="display: inline;"> Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical issues that arise due to evolving business logic and domain-specific requirements. To address this limitation, we propose LogiAgent, a novel approach for logical t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15079v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15079v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15079v1-abstract-full" style="display: none;"> Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical issues that arise due to evolving business logic and domain-specific requirements. To address this limitation, we propose LogiAgent, a novel approach for logical testing of REST systems. Built upon a large language model (LLM)-driven multi-agent framework, LogiAgent integrates a Test Scenario Generator, API Request Executor, and API Response Validator to collaboratively generate, execute, and validate API test scenarios. Unlike traditional testing methods that focus on status codes like 5xx, LogiAgent incorporates logical oracles that assess responses based on business logic, ensuring more comprehensive testing. The system is further enhanced by an Execution Memory component that stores historical API execution data for contextual consistency. We conduct extensive experiments across 12 real-world REST systems, demonstrating that LogiAgent effectively identifies 234 logical issues with an accuracy of 66.19%. Additionally, it basically excels in detecting server crashes and achieves superior test coverage compared to four state-of-the-art REST API testing tools. An ablation study confirms the significant contribution of LogiAgent's memory components to improving test coverage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15079v1-abstract-full').style.display = 'none'; document.getElementById('2503.15079v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14945">arXiv:2503.14945</a> <span> [<a href="https://arxiv.org/pdf/2503.14945">pdf</a>, <a href="https://arxiv.org/format/2503.14945">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"> Generating Multimodal Driving Scenes via Next-Scene Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanhao Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haoyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Tianwei Lin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+L">Lichao Huang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shujie Luo</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+R">Rui Wu</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+C">Congpei Qiu</a>, <a href="/search/cs?searchtype=author&query=Ke%2C+W">Wei Ke</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tong 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="2503.14945v2-abstract-short" style="display: inline;"> Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14945v2-abstract-full').style.display = 'inline'; document.getElementById('2503.14945v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14945v2-abstract-full" style="display: none;"> Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of map modality. With tokenized modalities, our scene sequence generation framework autoregressively predicts each scene while managing computational demands through a two-stage approach. The Temporal AutoRegressive (TAR) component captures inter-frame dynamics for each modality while the Ordered AutoRegressive (OAR) component aligns modalities within each scene by sequentially predicting tokens in a fixed order. To maintain coherence between map and ego-action modalities, we introduce the Action-aware Map Alignment (AMA) module, which applies a transformation based on the ego-action to maintain coherence between these modalities. Our framework effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements. Project page: https://yanhaowu.github.io/UMGen/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14945v2-abstract-full').style.display = 'none'; document.getElementById('2503.14945v2-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 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">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/2503.14927">arXiv:2503.14927</a> <span> [<a href="https://arxiv.org/pdf/2503.14927">pdf</a>, <a href="https://arxiv.org/format/2503.14927">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="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Dynamical Systems">math.DS</span> </div> </div> <p class="title is-5 mathjax"> Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yidan Wu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yu Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianan Zhang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+L">Li Jin</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="2503.14927v1-abstract-short" style="display: inline;"> We consider the traffic control problem of dynamic routing over parallel servers, which arises in a variety of engineering systems such as transportation and data transmission. We propose a semi-gradient, on-policy algorithm that learns an approximate optimal routing policy. The algorithm uses generic basis functions with flexible weights to approximate the value function across the unbounded stat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14927v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14927v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14927v1-abstract-full" style="display: none;"> We consider the traffic control problem of dynamic routing over parallel servers, which arises in a variety of engineering systems such as transportation and data transmission. We propose a semi-gradient, on-policy algorithm that learns an approximate optimal routing policy. The algorithm uses generic basis functions with flexible weights to approximate the value function across the unbounded state space. Consequently, the training process lacks Lipschitz continuity of the gradient, boundedness of the temporal-difference error, and a prior guarantee on ergodicity, which are the standard prerequisites in existing literature on reinforcement learning theory. To address this, we combine a Lyapunov approach and an ordinary differential equation-based method to jointly characterize the behavior of traffic state and approximation weights. Our theoretical analysis proves that the training scheme guarantees traffic state stability and ensures almost surely convergence of the weights to the approximate optimum. We also demonstrate via simulations that our algorithm attains significantly faster convergence than neural network-based methods with an insignificant approximation error. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14927v1-abstract-full').style.display = 'none'; document.getElementById('2503.14927v1-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">arXiv admin note: text overlap with arXiv:2404.09188</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14619">arXiv:2503.14619</a> <span> [<a href="https://arxiv.org/pdf/2503.14619">pdf</a>, <a href="https://arxiv.org/ps/2503.14619">ps</a>, <a href="https://arxiv.org/format/2503.14619">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> The broken sample problem revisited: Proof of a conjecture by Bai-Hsing and high-dimensional extensions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiao%2C+S">Simiao Jiao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yihong Wu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiaming 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="2503.14619v1-abstract-short" style="display: inline;"> We revisit the classical broken sample problem: Two samples of i.i.d. data points $\mathbf{X}=\{X_1,\cdots, X_n\}$ and $\mathbf{Y}=\{Y_1,\cdots,Y_m\}$ are observed without correspondence with $m\leq n$. Under the null hypothesis, $\mathbf{X}$ and $\mathbf{Y}$ are independent. Under the alternative hypothesis, $\mathbf{Y}$ is correlated with a random subsample of $\mathbf{X}$, in the sense that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14619v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14619v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14619v1-abstract-full" style="display: none;"> We revisit the classical broken sample problem: Two samples of i.i.d. data points $\mathbf{X}=\{X_1,\cdots, X_n\}$ and $\mathbf{Y}=\{Y_1,\cdots,Y_m\}$ are observed without correspondence with $m\leq n$. Under the null hypothesis, $\mathbf{X}$ and $\mathbf{Y}$ are independent. Under the alternative hypothesis, $\mathbf{Y}$ is correlated with a random subsample of $\mathbf{X}$, in the sense that $(X_{蟺(i)},Y_i)$'s are drawn independently from some bivariate distribution for some latent injection $蟺:[m] \to [n]$. Originally introduced by DeGroot, Feder, and Goel (1971) to model matching records in census data, this problem has recently gained renewed interest due to its applications in data de-anonymization, data integration, and target tracking. Despite extensive research over the past decades, determining the precise detection threshold has remained an open problem even for equal sample sizes ($m=n$). Assuming $m$ and $n$ grow proportionally, we show that the sharp threshold is given by a spectral and an $L_2$ condition of the likelihood ratio operator, resolving a conjecture of Bai and Hsing (2005) in the positive. These results are extended to high dimensions and settle the sharp detection thresholds for Gaussian and Bernoulli models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14619v1-abstract-full').style.display = 'none'; document.getElementById('2503.14619v1-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">35 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14495">arXiv:2503.14495</a> <span> [<a href="https://arxiv.org/pdf/2503.14495">pdf</a>, <a href="https://arxiv.org/format/2503.14495">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Temporal Consistency for LLM Reasoning Process Error Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+J">Jiacheng Guo</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yue Wu</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+J">Jiahao Qiu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+K">Kaixuan Huang</a>, <a href="/search/cs?searchtype=author&query=Juan%2C+X">Xinzhe Juan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Ling Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mengdi 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="2503.14495v1-abstract-short" style="display: inline;"> Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous assessment. Unlike one-round verification or multi-model debate approaches, our method leverages consistency in a sequence of self-reflection actions to improve verification accuracy. Empirical evaluations across diverse… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14495v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14495v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14495v1-abstract-full" style="display: none;"> Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous assessment. Unlike one-round verification or multi-model debate approaches, our method leverages consistency in a sequence of self-reflection actions to improve verification accuracy. Empirical evaluations across diverse mathematical process error identification benchmarks (Mathcheck, ProcessBench, and PRM800K) show consistent performance improvements over baseline methods. When applied to the recent DeepSeek R1 distilled models, our method demonstrates strong performance, enabling 7B/8B distilled models to outperform all 70B/72B models and GPT-4o on ProcessBench. Notably, the distilled 14B model with our method achieves performance comparable to Deepseek-R1. Our codes are available at https://github.com/jcguo123/Temporal-Consistency <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14495v1-abstract-full').style.display = 'none'; document.getElementById('2503.14495v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14476">arXiv:2503.14476</a> <span> [<a href="https://arxiv.org/pdf/2503.14476">pdf</a>, <a href="https://arxiv.org/format/2503.14476">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> DAPO: An Open-Source LLM Reinforcement Learning System at Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+Q">Qiying Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+R">Ruofei Zhu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+Y">Yufeng Yuan</a>, <a href="/search/cs?searchtype=author&query=Zuo%2C+X">Xiaochen Zuo</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+Y">Yu Yue</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+T">Tiantian Fan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Gaohong Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lingjun Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xin Liu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Haibin Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zhiqi Lin</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+B">Bole Ma</a>, <a href="/search/cs?searchtype=author&query=Sheng%2C+G">Guangming Sheng</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+Y">Yuxuan Tong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chi Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mofan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Hang Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jinhua Zhu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jiaze Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jiangjie Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chengyi Wang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+H">Hongli Yu</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+W">Weinan Dai</a> , et al. (10 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="2503.14476v1-abstract-short" style="display: inline;"> Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the $\textbf{D}$ecouple… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14476v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14476v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14476v1-abstract-full" style="display: none;"> Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the $\textbf{D}$ecoupled Clip and $\textbf{D}$ynamic s$\textbf{A}$mpling $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{DAPO}$) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B base model. Unlike previous works that withhold training details, we introduce four key techniques of our algorithm that make large-scale LLM RL a success. In addition, we open-source our training code, which is built on the verl framework, along with a carefully curated and processed dataset. These components of our open-source system enhance reproducibility and support future research in large-scale LLM RL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14476v1-abstract-full').style.display = 'none'; document.getElementById('2503.14476v1-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">Project Page: https://dapo-sia.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/2503.14258">arXiv:2503.14258</a> <span> [<a href="https://arxiv.org/pdf/2503.14258">pdf</a>, <a href="https://arxiv.org/format/2503.14258">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Su%2C+W">Weihang Su</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+B">Baoqing Yue</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+Q">Qingyao Ai</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yiran Hu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaqi Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Changyue Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yueyue Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiqun Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.14258v2-abstract-short" style="display: inline;"> This paper introduces JuDGE (Judgment Document Generation Evaluation), a novel benchmark for evaluating the performance of judgment document generation in the Chinese legal system. We define the task as generating a complete legal judgment document from the given factual description of the case. To facilitate this benchmark, we construct a comprehensive dataset consisting of factual descriptions f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14258v2-abstract-full').style.display = 'inline'; document.getElementById('2503.14258v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14258v2-abstract-full" style="display: none;"> This paper introduces JuDGE (Judgment Document Generation Evaluation), a novel benchmark for evaluating the performance of judgment document generation in the Chinese legal system. We define the task as generating a complete legal judgment document from the given factual description of the case. To facilitate this benchmark, we construct a comprehensive dataset consisting of factual descriptions from real legal cases, paired with their corresponding full judgment documents, which serve as the ground truth for evaluating the quality of generated documents. This dataset is further augmented by two external legal corpora that provide additional legal knowledge for the task: one comprising statutes and regulations, and the other consisting of a large collection of past judgment documents. In collaboration with legal professionals, we establish a comprehensive automated evaluation framework to assess the quality of generated judgment documents across various dimensions. We evaluate various baseline approaches, including few-shot in-context learning, fine-tuning, and a multi-source retrieval-augmented generation (RAG) approach, using both general and legal-domain LLMs. The experimental results demonstrate that, while RAG approaches can effectively improve performance in this task, there is still substantial room for further improvement. All the codes and datasets are available at: https://github.com/oneal2000/JuDGE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14258v2-abstract-full').style.display = 'none'; document.getElementById('2503.14258v2-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">v1</span> submitted 18 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/2503.13952">arXiv:2503.13952</a> <span> [<a href="https://arxiv.org/pdf/2503.13952">pdf</a>, <a href="https://arxiv.org/format/2503.13952">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"> SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xinqing Li</a>, <a href="/search/cs?searchtype=author&query=Song%2C+R">Ruiqi Song</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Q">Qingyu Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ye Wu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+N">Nanxin Zeng</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+Y">Yunfeng Ai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13952v1-abstract-short" style="display: inline;"> With the rapid advancement of autonomous driving technology, a lack of data has become a major obstacle to enhancing perception model accuracy. Researchers are now exploring controllable data generation using world models to diversify datasets. However, previous work has been limited to studying image generation quality on specific public datasets. There is still relatively little research on how… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13952v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13952v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13952v1-abstract-full" style="display: none;"> With the rapid advancement of autonomous driving technology, a lack of data has become a major obstacle to enhancing perception model accuracy. Researchers are now exploring controllable data generation using world models to diversify datasets. However, previous work has been limited to studying image generation quality on specific public datasets. There is still relatively little research on how to build data generation engines for real-world application scenes to achieve large-scale data generation for challenging scenes. In this paper, a simulator-conditioned scene generation engine based on world model is proposed. By constructing a simulation system consistent with real-world scenes, simulation data and labels, which serve as the conditions for data generation in the world model, for any scenes can be collected. It is a novel data generation pipeline by combining the powerful scene simulation capabilities of the simulation engine with the robust data generation capabilities of the world model. In addition, a benchmark with proportionally constructed virtual and real data, is provided for exploring the capabilities of world models in real-world scenes. Quantitative results show that these generated images significantly improve downstream perception models performance. Finally, we explored the generative performance of the world model in urban autonomous driving scenarios. All the data and code will be available at https://github.com/Li-Zn-H/SimWorld. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13952v1-abstract-full').style.display = 'none'; document.getElementById('2503.13952v1-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">8 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.8; I.2.10 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13891">arXiv:2503.13891</a> <span> [<a href="https://arxiv.org/pdf/2503.13891">pdf</a>, <a href="https://arxiv.org/format/2503.13891">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Where do Large Vision-Language Models Look at when Answering Questions? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xing%2C+X">Xiaoying Xing</a>, <a href="/search/cs?searchtype=author&query=Kuo%2C+C">Chia-Wen Kuo</a>, <a href="/search/cs?searchtype=author&query=Fuxin%2C+L">Li Fuxin</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+Y">Yulei Niu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+F">Fan Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Ming Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ying Wu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+L">Longyin Wen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Sijie Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13891v1-abstract-short" style="display: inline;"> Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do LVLMs rely on visual input, and which image regions contribute to their responses? It is non-trivial to interpret the free-form generation of LVLMs due to thei… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13891v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13891v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13891v1-abstract-full" style="display: none;"> Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do LVLMs rely on visual input, and which image regions contribute to their responses? It is non-trivial to interpret the free-form generation of LVLMs due to their complicated visual architecture (e.g., multiple encoders and multi-resolution) and variable-length outputs. In this paper, we extend existing heatmap visualization methods (e.g., iGOS++) to support LVLMs for open-ended visual question answering. We propose a method to select visually relevant tokens that reflect the relevance between generated answers and input image. Furthermore, we conduct a comprehensive analysis of state-of-the-art LVLMs on benchmarks designed to require visual information to answer. Our findings offer several insights into LVLM behavior, including the relationship between focus region and answer correctness, differences in visual attention across architectures, and the impact of LLM scale on visual understanding. The code and data are available at https://github.com/bytedance/LVLM_Interpretation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13891v1-abstract-full').style.display = 'none'; document.getElementById('2503.13891v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13883">arXiv:2503.13883</a> <span> [<a href="https://arxiv.org/pdf/2503.13883">pdf</a>, <a href="https://arxiv.org/format/2503.13883">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"> YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Ziyu Lin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yunfan Wu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yuhang Ma</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junzhou Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ronghui Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiaming Wu</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+G">Guodong Yin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+L">Liang Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13883v1-abstract-short" style="display: inline;"> Detecting traffic signs effectively under low-light conditions remains a significant challenge. To address this issue, we propose YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments. Firstly, we introduce the High-Resolution Feature Map for Small Object Detection (HRFM-TOD) module to address indistinct small-object features in low-li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13883v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13883v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13883v1-abstract-full" style="display: none;"> Detecting traffic signs effectively under low-light conditions remains a significant challenge. To address this issue, we propose YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments. Firstly, we introduce the High-Resolution Feature Map for Small Object Detection (HRFM-TOD) module to address indistinct small-object features in low-light scenarios. By leveraging high-resolution feature maps, HRFM-TOD effectively mitigates the feature dilution problem encountered in conventional PANet frameworks, thereby enhancing both detection accuracy and inference speed. Secondly, we develop the Multi-branch Feature Interaction Attention (MFIA) module, which facilitates deep feature interaction across multiple receptive fields in both channel and spatial dimensions, significantly improving the model's information extraction capabilities. Finally, we propose the Prior-Guided Enhancement Module (PGFE) to tackle common image quality challenges in low-light environments, such as noise, low contrast, and blurriness. This module employs prior knowledge to enrich image details and enhance visibility, substantially boosting detection performance. To support this research, we construct a novel dataset, the Chinese Nighttime Traffic Sign Sample Set (CNTSSS), covering diverse nighttime scenarios, including urban, highway, and rural environments under varying weather conditions. Experimental evaluations demonstrate that YOLO-LLTS achieves state-of-the-art performance, outperforming the previous best methods by 2.7% mAP50 and 1.6% mAP50:95 on TT100K-night, 1.3% mAP50 and 1.9% mAP50:95 on CNTSSS, and achieving superior results on the CCTSDB2021 dataset. Moreover, deployment experiments on edge devices confirm the real-time applicability and effectiveness of our proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13883v1-abstract-full').style.display = 'none'; document.getElementById('2503.13883v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13684">arXiv:2503.13684</a> <span> [<a href="https://arxiv.org/pdf/2503.13684">pdf</a>, <a href="https://arxiv.org/format/2503.13684">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"> FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+M">Minghan Li</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+C">Chenxi Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yichen Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lei Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mengyu 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="2503.13684v1-abstract-short" style="display: inline;"> Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained video editing is crucial for enabling precise, object-level modifications while maintaining context and temporal consistency. To address this, we introduce FiVE,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13684v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13684v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13684v1-abstract-full" style="display: none;"> Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained video editing is crucial for enabling precise, object-level modifications while maintaining context and temporal consistency. To address this, we introduce FiVE, a Fine-grained Video Editing Benchmark for evaluating emerging diffusion and rectified flow models. Our benchmark includes 74 real-world videos and 26 generated videos, featuring 6 fine-grained editing types, 420 object-level editing prompt pairs, and their corresponding masks. Additionally, we adapt the latest rectified flow (RF) T2V generation models, Pyramid-Flow and Wan2.1, by introducing FlowEdit, resulting in training-free and inversion-free video editing models Pyramid-Edit and Wan-Edit. We evaluate five diffusion-based and two RF-based editing methods on our FiVE benchmark using 15 metrics, covering background preservation, text-video similarity, temporal consistency, video quality, and runtime. To further enhance object-level evaluation, we introduce FiVE-Acc, a novel metric leveraging Vision-Language Models (VLMs) to assess the success of fine-grained video editing. Experimental results demonstrate that RF-based editing significantly outperforms diffusion-based methods, with Wan-Edit achieving the best overall performance and exhibiting the least sensitivity to hyperparameters. More video demo available on the anonymous website: https://sites.google.com/view/five-benchmark <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13684v1-abstract-full').style.display = 'none'; document.getElementById('2503.13684v1-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">24 pages, 14 figures, 16 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13011">arXiv:2503.13011</a> <span> [<a href="https://arxiv.org/pdf/2503.13011">pdf</a>, <a href="https://arxiv.org/format/2503.13011">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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Sensorless Remote Center of Motion Misalignment Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+H">Hao Yang</a>, <a href="/search/cs?searchtype=author&query=Al-Zogbi%2C+L">Lidia Al-Zogbi</a>, <a href="/search/cs?searchtype=author&query=Yildiz%2C+A">Ahmet Yildiz</a>, <a href="/search/cs?searchtype=author&query=Simaan%2C+N">Nabil Simaan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J+Y">Jie Ying Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13011v1-abstract-short" style="display: inline;"> Laparoscopic surgery constrains instrument motion around a fixed pivot point at the incision into a patient to minimize tissue trauma. Surgical robots achieve this through either hardware to software-based remote center of motion (RCM) constraints. However, accurate RCM alignment is difficult due to manual trocar placement, patient motion, and tissue deformation. Misalignment between the robot's R… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13011v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13011v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13011v1-abstract-full" style="display: none;"> Laparoscopic surgery constrains instrument motion around a fixed pivot point at the incision into a patient to minimize tissue trauma. Surgical robots achieve this through either hardware to software-based remote center of motion (RCM) constraints. However, accurate RCM alignment is difficult due to manual trocar placement, patient motion, and tissue deformation. Misalignment between the robot's RCM point and the patient incision site can cause unsafe forces at the incision site. This paper presents a sensorless force estimation-based framework for dynamically assessing and optimizing RCM misalignment in robotic surgery. Our experiments demonstrate that misalignment exceeding 20 mm can generate large enough forces to potentially damage tissue, emphasizing the need for precise RCM positioning. For misalignment $D\geq $ 20 mm, our optimization algorithm estimates the RCM offset with an absolute error within 5 mm. Accurate RCM misalignment estimation is a step toward automated RCM misalignment compensation, enhancing safety and reducing tissue damage in robotic-assisted laparoscopic surgery. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13011v1-abstract-full').style.display = 'none'; document.getElementById('2503.13011v1-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/2503.12958">arXiv:2503.12958</a> <span> [<a href="https://arxiv.org/pdf/2503.12958">pdf</a>, <a href="https://arxiv.org/format/2503.12958">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> FedSDP: Explainable Differential Privacy in Federated Learning via Shapley Values </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunbo Li</a>, <a href="/search/cs?searchtype=author&query=Gui%2C+J">Jiaping Gui</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yue Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12958v1-abstract-short" style="display: inline;"> Federated learning (FL) enables participants to store data locally while collaborating in training, yet it remains vulnerable to privacy attacks, such as data reconstruction. Existing differential privacy (DP) technologies inject noise dynamically into the training process to mitigate the impact of excessive noise. However, this dynamic scheduling is often grounded in factors indirectly related to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12958v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12958v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12958v1-abstract-full" style="display: none;"> Federated learning (FL) enables participants to store data locally while collaborating in training, yet it remains vulnerable to privacy attacks, such as data reconstruction. Existing differential privacy (DP) technologies inject noise dynamically into the training process to mitigate the impact of excessive noise. However, this dynamic scheduling is often grounded in factors indirectly related to privacy, making it difficult to clearly explain the intricate relationship between dynamic noise adjustments and privacy requirements. To address this issue, we propose FedSDP, a novel and explainable DP-based privacy protection mechanism that guides noise injection based on privacy contribution. Specifically, FedSDP leverages Shapley values to assess the contribution of private attributes to local model training and dynamically adjusts the amount of noise injected accordingly. By providing theoretical insights into the injection of varying scales of noise into local training, FedSDP enhances interpretability. Extensive experiments demonstrate that FedSDP can achieve a superior balance between privacy preservation and model performance, surpassing state-of-the-art (SOTA) solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12958v1-abstract-full').style.display = 'none'; document.getElementById('2503.12958v1-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/2503.12833">arXiv:2503.12833</a> <span> [<a href="https://arxiv.org/pdf/2503.12833">pdf</a>, <a href="https://arxiv.org/format/2503.12833">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> MT-PCR: Leveraging Modality Transformation for Large-Scale Point Cloud Registration with Limited Overlap </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yilong Wu</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+Y">Yifan Duan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuxi Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinran Zhang</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yedong Shen</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+J">Jianmin Ji</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yanyong Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lu 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="2503.12833v1-abstract-short" style="display: inline;"> Large-scale scene point cloud registration with limited overlap is a challenging task due to computational load and constrained data acquisition. To tackle these issues, we propose a point cloud registration method, MT-PCR, based on Modality Transformation. MT-PCR leverages a BEV capturing the maximal overlap information to improve the accuracy and utilizes images to provide complementary spatial… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12833v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12833v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12833v1-abstract-full" style="display: none;"> Large-scale scene point cloud registration with limited overlap is a challenging task due to computational load and constrained data acquisition. To tackle these issues, we propose a point cloud registration method, MT-PCR, based on Modality Transformation. MT-PCR leverages a BEV capturing the maximal overlap information to improve the accuracy and utilizes images to provide complementary spatial features. Specifically, MT-PCR converts 3D point clouds to BEV images and eastimates correspondence by 2D image keypoints extraction and matching. Subsequently, the 2D correspondence estimates are then transformed back to 3D point clouds using inverse mapping. We have applied MT-PCR to Terrestrial Laser Scanning and Aerial Laser Scanning point cloud registration on the GrAco dataset, involving 8 low-overlap, square-kilometer scale registration scenarios. Experiments and comparisons with commonly used methods demonstrate that MT-PCR can achieve superior accuracy and robustness in large-scale scenes with limited overlap. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12833v1-abstract-full').style.display = 'none'; document.getElementById('2503.12833v1-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">8 pages, 5 figures, ICRA2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12790">arXiv:2503.12790</a> <span> [<a href="https://arxiv.org/pdf/2503.12790">pdf</a>, <a href="https://arxiv.org/format/2503.12790">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</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"> Quantum-Enhanced LLM Efficient Fine Tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kong%2C+X">Xiaofei Kong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lei Li</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+M">Menghan Dou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhaoyun Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuchun Wu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+G">Guoping Guo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12790v1-abstract-short" style="display: inline;"> Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models via low-rank matrix approximation, which is effective in many scenarios. However, its low-rank representation capacity is constrained in complex tasks or high-rank dependency settings, potentially limiting model adaptability. Addressing the expressive bottleneck of classical low-rank approximation in fine-tunin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12790v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12790v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12790v1-abstract-full" style="display: none;"> Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models via low-rank matrix approximation, which is effective in many scenarios. However, its low-rank representation capacity is constrained in complex tasks or high-rank dependency settings, potentially limiting model adaptability. Addressing the expressive bottleneck of classical low-rank approximation in fine-tuning large language models, this paper proposes a parameter-efficient fine-tuning method based on a Quantum Weighted Tensor Hybrid Network (QWTHN), which leverages Quantum Neural Network (QNN). The study investigates quantum-classical hybrid parameter-efficient fine-tuning in low-rank spaces. QWTHN decomposes pre-trained weights into quantum neural network and tensor network representations, utilizing quantum state superposition and other methods to break through classical rank limitations. Experiments show that the proposed quantum fine-tuning technique for large models approaches or even surpasses the parameter efficiency of LoRA. On the CPsyCounD and R1-Distill-SFT datasets, QWTHN, compared to classical LoRA, reduces training loss by up to 15% while using 76% fewer parameters, and achieves an 8.4% performance improvement on the CPsyCounD test set. This research not only realizes lightweight and efficient adaptation of quantum resources to billion-parameter models but also validates the practical path of quantum hardware driven by large model tasks, laying the first engineering-ready technical foundation for future quantum-enhanced AGI systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12790v1-abstract-full').style.display = 'none'; document.getElementById('2503.12790v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12287">arXiv:2503.12287</a> <span> [<a href="https://arxiv.org/pdf/2503.12287">pdf</a>, <a href="https://arxiv.org/format/2503.12287">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> SharedAssembly: A Data Collection Approach via Shared Tele-Assembly </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yansong Wu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yu Chen</a>, <a href="/search/cs?searchtype=author&query=Sadeghian%2C+H">Hamid Sadeghian</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+F">Fan Wu</a>, <a href="/search/cs?searchtype=author&query=Bing%2C+Z">Zhenshan Bing</a>, <a href="/search/cs?searchtype=author&query=Haddadin%2C+S">Sami Haddadin</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6nig%2C+A">Alexander K枚nig</a>, <a href="/search/cs?searchtype=author&query=Knoll%2C+A">Alois Knoll</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="2503.12287v1-abstract-short" style="display: inline;"> Assembly is a fundamental skill for robots in both modern manufacturing and service robotics. Existing datasets aim to address the data bottleneck in training general-purpose robot models, falling short of capturing contact-rich assembly tasks. To bridge this gap, we introduce SharedAssembly, a novel bilateral teleoperation approach with shared autonomy for scalable assembly execution and data col… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12287v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12287v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12287v1-abstract-full" style="display: none;"> Assembly is a fundamental skill for robots in both modern manufacturing and service robotics. Existing datasets aim to address the data bottleneck in training general-purpose robot models, falling short of capturing contact-rich assembly tasks. To bridge this gap, we introduce SharedAssembly, a novel bilateral teleoperation approach with shared autonomy for scalable assembly execution and data collection. User studies demonstrate that the proposed approach enhances both success rates and efficiency, achieving a 97.0% success rate across various sub-millimeter-level assembly tasks. Notably, novice and intermediate users achieve performance comparable to experts using baseline teleoperation methods, significantly enhancing large-scale data collection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12287v1-abstract-full').style.display = 'none'; document.getElementById('2503.12287v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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">7 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T40 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.9 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12063">arXiv:2503.12063</a> <span> [<a href="https://arxiv.org/pdf/2503.12063">pdf</a>, <a href="https://arxiv.org/format/2503.12063">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"> DLA-Count: Dynamic Label Assignment Network for Dense Cell Distribution Counting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yuqing Yan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yirui Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12063v1-abstract-short" style="display: inline;"> Cell counting remains a fundamental yet challenging task in medical and biological research due to the diverse morphology of cells, their dense distribution, and variations in image quality. We present DLA-Count, a breakthrough approach to cell counting that introduces three key innovations: (1) K-adjacent Hungarian Matching (KHM), which dramatically improves cell matching in dense regions, (2) Mu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12063v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12063v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12063v1-abstract-full" style="display: none;"> Cell counting remains a fundamental yet challenging task in medical and biological research due to the diverse morphology of cells, their dense distribution, and variations in image quality. We present DLA-Count, a breakthrough approach to cell counting that introduces three key innovations: (1) K-adjacent Hungarian Matching (KHM), which dramatically improves cell matching in dense regions, (2) Multi-scale Deformable Gaussian Convolution (MDGC), which adapts to varying cell morphologies, and (3) Gaussian-enhanced Feature Decoder (GFD) for efficient multi-scale feature fusion. Our extensive experiments on four challenging cell counting datasets (ADI, MBM, VGG, and DCC) demonstrate that our method outperforms previous methods across diverse datasets, with improvements in Mean Absolute Error of up to 46.7\% on ADI and 42.5\% on MBM datasets. Our code is available at https://anonymous.4open.science/r/DLA-Count. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12063v1-abstract-full').style.display = 'none'; document.getElementById('2503.12063v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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/2503.12061">arXiv:2503.12061</a> <span> [<a href="https://arxiv.org/pdf/2503.12061">pdf</a>, <a href="https://arxiv.org/format/2503.12061">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"> EHNet: An Efficient Hybrid Network for Crowd Counting and Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yuqing Yan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yirui Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12061v1-abstract-short" style="display: inline;"> In recent years, crowd counting and localization have become crucial techniques in computer vision, with applications spanning various domains. The presence of multi-scale crowd distributions within a single image remains a fundamental challenge in crowd counting tasks. To address these challenges, we introduce the Efficient Hybrid Network (EHNet), a novel framework for efficient crowd counting an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12061v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12061v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12061v1-abstract-full" style="display: none;"> In recent years, crowd counting and localization have become crucial techniques in computer vision, with applications spanning various domains. The presence of multi-scale crowd distributions within a single image remains a fundamental challenge in crowd counting tasks. To address these challenges, we introduce the Efficient Hybrid Network (EHNet), a novel framework for efficient crowd counting and localization. By reformulating crowd counting into a point regression framework, EHNet leverages the Spatial-Position Attention Module (SPAM) to capture comprehensive spatial contexts and long-range dependencies. Additionally, we develop an Adaptive Feature Aggregation Module (AFAM) to effectively fuse and harmonize multi-scale feature representations. Building upon these, we introduce the Multi-Scale Attentive Decoder (MSAD). Experimental results on four benchmark datasets demonstrate that EHNet achieves competitive performance with reduced computational overhead, outperforming existing methods on ShanghaiTech Part \_A, ShanghaiTech Part \_B, UCF-CC-50, and UCF-QNRF. Our code is in https://anonymous.4open.science/r/EHNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12061v1-abstract-full').style.display = 'none'; document.getElementById('2503.12061v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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/2503.12016">arXiv:2503.12016</a> <span> [<a href="https://arxiv.org/pdf/2503.12016">pdf</a>, <a href="https://arxiv.org/format/2503.12016">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Survey on Federated Fine-tuning of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yebo Wu</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+C">Chunlin Tian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jingguang Li</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">He Sun</a>, <a href="/search/cs?searchtype=author&query=Tam%2C+K">Kahou Tam</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Li Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chengzhong 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="2503.12016v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, with fine-tuning playing a pivotal role in adapting them to specific downstream applications. Federated Learning (FL) offers a promising approach that enables collaborative model adaptation while ensuring data privacy, i.e., FedLLM. In this survey, we provide a systematic and thorough review of the integrat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12016v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12016v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12016v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, with fine-tuning playing a pivotal role in adapting them to specific downstream applications. Federated Learning (FL) offers a promising approach that enables collaborative model adaptation while ensuring data privacy, i.e., FedLLM. In this survey, we provide a systematic and thorough review of the integration of LLMs with FL. Specifically, we first trace the historical evolution of both LLMs and FL, while summarizing relevant prior surveys. We then present an in-depth analysis of the fundamental challenges encountered in deploying FedLLM. Following this, we conduct an extensive study of existing parameter-efficient fine-tuning (PEFT) methods and explore their applicability in FL. Furthermore, we introduce a comprehensive evaluation benchmark to rigorously assess FedLLM performance and discuss its diverse real-world applications across multiple domains. Finally, we identify critical open challenges and outline promising research directions to drive future advancements in FedLLM. We maintain an active \href{https://github.com/Clin0212/Awesome-Federated-LLM-Learning}{GitHub repository} tracking cutting-edge advancements. This survey serves as a foundational resource for researchers and practitioners, offering insights into the evolving landscape of federated fine-tuning for LLMs while guiding future innovations in privacy-preserving AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12016v1-abstract-full').style.display = 'none'; document.getElementById('2503.12016v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 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/2503.11709">arXiv:2503.11709</a> <span> [<a href="https://arxiv.org/pdf/2503.11709">pdf</a>, <a href="https://arxiv.org/format/2503.11709">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"> Conformal Prediction and Human Decision Making </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hullman%2C+J">Jessica Hullman</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yifan Wu</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+D">Dawei Xie</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Ziyang Guo</a>, <a href="/search/cs?searchtype=author&query=Gelman%2C+A">Andrew Gelman</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="2503.11709v2-abstract-short" style="display: inline;"> Methods to quantify uncertainty in predictions from arbitrary models are in demand in high-stakes domains like medicine and finance. Conformal prediction has emerged as a popular method for producing a set of predictions with specified average coverage, in place of a single prediction and confidence value. However, the value of conformal prediction sets to assist human decisions remains elusive du… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11709v2-abstract-full').style.display = 'inline'; document.getElementById('2503.11709v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11709v2-abstract-full" style="display: none;"> Methods to quantify uncertainty in predictions from arbitrary models are in demand in high-stakes domains like medicine and finance. Conformal prediction has emerged as a popular method for producing a set of predictions with specified average coverage, in place of a single prediction and confidence value. However, the value of conformal prediction sets to assist human decisions remains elusive due to the murky relationship between coverage guarantees and decision makers' goals and strategies. How should we think about conformal prediction sets as a form of decision support? We outline a decision theoretic framework for evaluating predictive uncertainty as informative signals, then contrast what can be said within this framework about idealized use of calibrated probabilities versus conformal prediction sets. Informed by prior empirical results and theories of human decisions under uncertainty, we formalize a set of possible strategies by which a decision maker might use a prediction set. We identify ways in which conformal prediction sets and posthoc predictive uncertainty quantification more broadly are in tension with common goals and needs in human-AI decision making. We give recommendations for future research in predictive uncertainty quantification to support human decision makers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11709v2-abstract-full').style.display = 'none'; document.getElementById('2503.11709v2-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">v1</span> submitted 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/2503.11490">arXiv:2503.11490</a> <span> [<a href="https://arxiv.org/pdf/2503.11490">pdf</a>, <a href="https://arxiv.org/format/2503.11490">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3680207.3723465">10.1145/3680207.3723465 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> PassiveBLE: Towards Fully Commodity-Compatible BLE Backscatter </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dong%2C+H">Huixin Dong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yijie Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Feiyu Li</a>, <a href="/search/cs?searchtype=author&query=Kuang%2C+W">Wei Kuang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yuan He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qian Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wei 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="2503.11490v1-abstract-short" style="display: inline;"> Bluetooth Low Energy (BLE) backscatter is a promising candidate for battery-free Internet of Things (IoT) applications. Unlike existing commodity-level BLE backscatter systems that only enable one-shot communication through BLE advertising packets, we propose PassiveBLE, a backscatter system that can establish authentic and fully compatible BLE connections on data channels. The key enabling techni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11490v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11490v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11490v1-abstract-full" style="display: none;"> Bluetooth Low Energy (BLE) backscatter is a promising candidate for battery-free Internet of Things (IoT) applications. Unlike existing commodity-level BLE backscatter systems that only enable one-shot communication through BLE advertising packets, we propose PassiveBLE, a backscatter system that can establish authentic and fully compatible BLE connections on data channels. The key enabling techniques include (i) a synchronization circuit that can wake up tags and activate backscatter communications with symbol-level accuracy to facilitate BLE data packet generation; (ii) a distributed coding scheme that offloads the major encoding and processing burdens from tags to the excitation source while achieving high throughput; (iii) a BLE connection scheduler to enable fully compatible BLE connection interactions, including connection establishment, maintenance and termination for multiple backscatter tags. We prototype PassiveBLE tags with off-the-shelf components and also convert the circuits and control logic into ASIC design sketch, whose power consumptions are 491 uW and 9.9 uW, respectively. Experimental results demonstrate that PassiveBLE achieves a success rate of over 99.9% in establishing commodity BLE connections. PassiveBLE also achieves commodity-compatible BLE communication with a high goodput of up to 974 kbps in LE 2M PHY mode and 532 kbps in LE 1M PHY mode, which is about 63.3 times higher than the previous commodity-level BLE backscatter system in the same mode. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11490v1-abstract-full').style.display = 'none'; document.getElementById('2503.11490v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 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, 32 figures, to appear in ACM MobiCom 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/2503.11224">arXiv:2503.11224</a> <span> [<a href="https://arxiv.org/pdf/2503.11224">pdf</a>, <a href="https://arxiv.org/format/2503.11224">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lv%2C+X">Xingtai Lv</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Youbang Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+S">Shang Qu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xuekai Zhu</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+Y">Yuchen Fan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi Wu</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+E">Ermo Hua</a>, <a href="/search/cs?searchtype=author&query=Long%2C+X">Xinwei Long</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+N">Ning Ding</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+B">Bowen 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="2503.11224v1-abstract-short" style="display: inline;"> State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts, demonstrating comparable performances with significant efficiency gains. In this survey, we provide a coherent and systematic overview for SSMs, including their… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11224v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11224v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11224v1-abstract-full" style="display: none;"> State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts, demonstrating comparable performances with significant efficiency gains. In this survey, we provide a coherent and systematic overview for SSMs, including their theoretical motivations, mathematical formulations, comparison with existing model classes, and various applications. We divide the SSM series into three main sections, providing a detailed introduction to the original SSM, the structured SSM represented by S4, and the selective SSM typified by Mamba. We put an emphasis on technicality, and highlight the various key techniques introduced to address the effectiveness and efficiency of SSMs. We hope this manuscript serves as an introduction for researchers to explore the theoretical foundations of SSMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11224v1-abstract-full').style.display = 'none'; document.getElementById('2503.11224v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 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/2503.11219">arXiv:2503.11219</a> <span> [<a href="https://arxiv.org/pdf/2503.11219">pdf</a>, <a href="https://arxiv.org/format/2503.11219">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"> MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yansheng Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuning Wu</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+G">Gong Cheng</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+C">Chao Tao</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+B">Bo Dang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiahao Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chuge Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiting Liu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+X">Xu Tang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+J">Jiayi Ma</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongjun 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="2503.11219v1-abstract-short" style="display: inline;"> Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11219v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11219v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11219v1-abstract-full" style="display: none;"> Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-inscene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for finegrained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11219v1-abstract-full').style.display = 'none'; document.getElementById('2503.11219v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 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/2503.11081">arXiv:2503.11081</a> <span> [<a href="https://arxiv.org/pdf/2503.11081">pdf</a>, <a href="https://arxiv.org/format/2503.11081">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Pingrui Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xianqiang Gao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuhan Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kehui Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Dong Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhigang Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+B">Bin Zhao</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yan Ding</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xuelong 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="2503.11081v1-abstract-short" style="display: inline;"> In mobile manipulation, navigation and manipulation are often treated as separate problems, resulting in a significant gap between merely approaching an object and engaging with it effectively. Many navigation approaches primarily define success by proximity to the target, often overlooking the necessity for optimal positioning that facilitates subsequent manipulation. To address this, we introduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11081v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11081v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11081v1-abstract-full" style="display: none;"> In mobile manipulation, navigation and manipulation are often treated as separate problems, resulting in a significant gap between merely approaching an object and engaging with it effectively. Many navigation approaches primarily define success by proximity to the target, often overlooking the necessity for optimal positioning that facilitates subsequent manipulation. To address this, we introduce MoMa-Kitchen, a benchmark dataset comprising over 100k samples that provide training data for models to learn optimal final navigation positions for seamless transition to manipulation. Our dataset includes affordance-grounded floor labels collected from diverse kitchen environments, in which robotic mobile manipulators of different models attempt to grasp target objects amidst clutter. Using a fully automated pipeline, we simulate diverse real-world scenarios and generate affordance labels for optimal manipulation positions. Visual data are collected from RGB-D inputs captured by a first-person view camera mounted on the robotic arm, ensuring consistency in viewpoint during data collection. We also develop a lightweight baseline model, NavAff, for navigation affordance grounding that demonstrates promising performance on the MoMa-Kitchen benchmark. Our approach enables models to learn affordance-based final positioning that accommodates different arm types and platform heights, thereby paving the way for more robust and generalizable integration of navigation and manipulation in embodied AI. Project page: \href{https://momakitchen.github.io/}{https://momakitchen.github.io/}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11081v1-abstract-full').style.display = 'none'; document.getElementById('2503.11081v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 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/2503.10928">arXiv:2503.10928</a> <span> [<a href="https://arxiv.org/pdf/2503.10928">pdf</a>, <a href="https://arxiv.org/format/2503.10928">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Design and Development of the MeCO Open-Source Autonomous Underwater Vehicle </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Widhalm%2C+D">David Widhalm</a>, <a href="/search/cs?searchtype=author&query=Ohnsted%2C+C">Cory Ohnsted</a>, <a href="/search/cs?searchtype=author&query=Knutson%2C+C">Corey Knutson</a>, <a href="/search/cs?searchtype=author&query=Kutzke%2C+D">Demetrious Kutzke</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+S">Sakshi Singh</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+R">Rishi Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Schwidder%2C+G">Grant Schwidder</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Ying-Kun Wu</a>, <a href="/search/cs?searchtype=author&query=Sattar%2C+J">Junaed Sattar</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="2503.10928v1-abstract-short" style="display: inline;"> We present MeCO, the Medium Cost Open-source autonomous underwater vehicle (AUV), a versatile autonomous vehicle designed to support research and development in underwater human-robot interaction (UHRI) and marine robotics in general. An inexpensive platform to build compared to similarly-capable AUVs, the MeCO design and software are released under open-source licenses, making it a cost effective… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10928v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10928v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10928v1-abstract-full" style="display: none;"> We present MeCO, the Medium Cost Open-source autonomous underwater vehicle (AUV), a versatile autonomous vehicle designed to support research and development in underwater human-robot interaction (UHRI) and marine robotics in general. An inexpensive platform to build compared to similarly-capable AUVs, the MeCO design and software are released under open-source licenses, making it a cost effective, extensible, and open platform. It is equipped with UHRI-focused systems, such as front and side facing displays, light-based communication devices, a transducer for acoustic interaction, and stereo vision, in addition to typical AUV sensing and actuation components. Additionally, MeCO is capable of real-time deep learning inference using the latest edge computing devices, while maintaining low-latency, closed-loop control through high-performance microcontrollers. MeCO is designed from the ground up for modularity in internal electronics, external payloads, and software architecture, exploiting open-source robotics and containerarization tools. We demonstrate the diverse capabilities of MeCO through simulated, closed-water, and open-water experiments. All resources necessary to build and run MeCO, including software and hardware design, have been made publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10928v1-abstract-full').style.display = 'none'; document.getElementById('2503.10928v1-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/2503.10305">arXiv:2503.10305</a> <span> [<a href="https://arxiv.org/pdf/2503.10305">pdf</a>, <a href="https://arxiv.org/format/2503.10305">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"> Eye on the Target: Eye Tracking Meets Rodent Tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mededovic%2C+E">Emil Mededovic</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuli Wu</a>, <a href="/search/cs?searchtype=author&query=Konermann%2C+H">Henning Konermann</a>, <a href="/search/cs?searchtype=author&query=Kopaczka%2C+M">Marcin Kopaczka</a>, <a href="/search/cs?searchtype=author&query=Schulz%2C+M">Mareike Schulz</a>, <a href="/search/cs?searchtype=author&query=Tolba%2C+R">Rene Tolba</a>, <a href="/search/cs?searchtype=author&query=Stegmaier%2C+J">Johannes Stegmaier</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="2503.10305v1-abstract-short" style="display: inline;"> Analyzing animal behavior from video recordings is crucial for scientific research, yet manual annotation remains labor-intensive and prone to subjectivity. Efficient segmentation methods are needed to automate this process while maintaining high accuracy. In this work, we propose a novel pipeline that utilizes eye-tracking data from Aria glasses to generate prompt points, which are then used to p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10305v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10305v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10305v1-abstract-full" style="display: none;"> Analyzing animal behavior from video recordings is crucial for scientific research, yet manual annotation remains labor-intensive and prone to subjectivity. Efficient segmentation methods are needed to automate this process while maintaining high accuracy. In this work, we propose a novel pipeline that utilizes eye-tracking data from Aria glasses to generate prompt points, which are then used to produce segmentation masks via a fast zero-shot segmentation model. Additionally, we apply post-processing to refine the prompts, leading to improved segmentation quality. Through our approach, we demonstrate that combining eye-tracking-based annotation with smart prompt refinement can enhance segmentation accuracy, achieving an improvement of 70.6% from 38.8 to 66.2 in the Jaccard Index for segmentation results in the rats dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10305v1-abstract-full').style.display = 'none'; document.getElementById('2503.10305v1-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/2503.10214">arXiv:2503.10214</a> <span> [<a href="https://arxiv.org/pdf/2503.10214">pdf</a>, <a href="https://arxiv.org/format/2503.10214">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"> Singular Value Fine-tuning for Few-Shot Class-Incremental Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhiwu Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yichen Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Renzhen Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Haokun Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Quanziang Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Q">Qian Zhao</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+D">Deyu Meng</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="2503.10214v1-abstract-short" style="display: inline;"> Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL (FSCIL) setting further complicates this by providing only a limited number of samples for each new class, increasing the risk of overfitting in addition to standard CIL challenges. While catastrophic forgetting has been… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10214v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10214v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10214v1-abstract-full" style="display: none;"> Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL (FSCIL) setting further complicates this by providing only a limited number of samples for each new class, increasing the risk of overfitting in addition to standard CIL challenges. While catastrophic forgetting has been extensively studied, overfitting in FSCIL, especially with large foundation models, has received less attention. To fill this gap, we propose the Singular Value Fine-tuning for FSCIL (SVFCL) and compared it with existing approaches for adapting foundation models to FSCIL, which primarily build on Parameter Efficient Fine-Tuning (PEFT) methods like prompt tuning and Low-Rank Adaptation (LoRA). Specifically, SVFCL applies singular value decomposition to the foundation model weights, keeping the singular vectors fixed while fine-tuning the singular values for each task, and then merging them. This simple yet effective approach not only alleviates the forgetting problem but also mitigates overfitting more effectively while significantly reducing trainable parameters. Extensive experiments on four benchmark datasets, along with visualizations and ablation studies, validate the effectiveness of SVFCL. The code will be made available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10214v1-abstract-full').style.display = 'none'; document.getElementById('2503.10214v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.10149">arXiv:2503.10149</a> <span> [<a href="https://arxiv.org/pdf/2503.10149">pdf</a>, <a href="https://arxiv.org/format/2503.10149">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"> Unlocking Generalization Power in LiDAR Point Cloud Registration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+Z">Zhenxuan Zeng</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qiao Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L+Y">Lin Yuanbo Wu</a>, <a href="/search/cs?searchtype=author&query=An%2C+P">Pei An</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiaqi Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Ji Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Peng 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="2503.10149v1-abstract-short" style="display: inline;"> In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications. However, current methods fall short in achieving this level of generalization. To address these limitations, we propose UGP, a pruned framework designed to enhance… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10149v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10149v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10149v1-abstract-full" style="display: none;"> In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications. However, current methods fall short in achieving this level of generalization. To address these limitations, we propose UGP, a pruned framework designed to enhance generalization power for LiDAR point cloud registration. The core insight in UGP is the elimination of cross-attention mechanisms to improve generalization, allowing the network to concentrate on intra-frame feature extraction. Additionally, we introduce a progressive self-attention module to reduce ambiguity in large-scale scenes and integrate Bird's Eye View (BEV) features to incorporate semantic information about scene elements. Together, these enhancements significantly boost the network's generalization performance. We validated our approach through various generalization experiments in multiple outdoor scenes. In cross-distance generalization experiments on KITTI and nuScenes, UGP achieved state-of-the-art mean Registration Recall rates of 94.5% and 91.4%, respectively. In cross-dataset generalization from nuScenes to KITTI, UGP achieved a state-of-the-art mean Registration Recall of 90.9%. Code will be available at https://github.com/peakpang/UGP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10149v1-abstract-full').style.display = 'none'; document.getElementById('2503.10149v1-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> <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/2503.10125">arXiv:2503.10125</a> <span> [<a href="https://arxiv.org/pdf/2503.10125">pdf</a>, <a href="https://arxiv.org/format/2503.10125">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yi Wu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Lingting Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lei Liu</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+W">Wandi Qiao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Ziqiang Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Lequan Yu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bin 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="2503.10125v1-abstract-short" style="display: inline;"> Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these models initially struggle with subject-driven image generation compared to dominant diffusion models.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10125v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10125v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10125v1-abstract-full" style="display: none;"> Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these models initially struggle with subject-driven image generation compared to dominant diffusion models. To address this limitation, we introduce Proxy-Tuning, leveraging diffusion models to enhance AR models' capabilities in subject-specific image generation. Our method reveals a striking weak-to-strong phenomenon: fine-tuned AR models consistently outperform their diffusion model supervisors in both subject fidelity and prompt adherence. We analyze this performance shift and identify scenarios where AR models excel, particularly in multi-subject compositions and contextual understanding. This work not only demonstrates impressive results in subject-driven AR image generation, but also unveils the potential of weak-to-strong generalization in the image generation domain, contributing to a deeper understanding of different architectures' strengths and limitations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10125v1-abstract-full').style.display = 'none'; document.getElementById('2503.10125v1-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/2503.10036">arXiv:2503.10036</a> <span> [<a href="https://arxiv.org/pdf/2503.10036">pdf</a>, <a href="https://arxiv.org/format/2503.10036">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> CCaaLF: Concurrency Control as a Learnable Function </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+H">Hexiang Pan</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+S">Shaofeng Cai</a>, <a href="/search/cs?searchtype=author&query=Dinh%2C+T+T+A">Tien Tuan Anh Dinh</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuncheng Wu</a>, <a href="/search/cs?searchtype=author&query=Chee%2C+Y+M">Yeow Meng Chee</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">Gang Chen</a>, <a href="/search/cs?searchtype=author&query=Ooi%2C+B+C">Beng Chin Ooi</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="2503.10036v3-abstract-short" style="display: inline;"> Concurrency control (CC) algorithms are important in modern transactional databases, as they enable high performance by executing transactions concurrently while ensuring correctness. However, state-of-the-art CC algorithms struggle to perform well across diverse workloads, and most do not consider workload drifts. In this paper, we propose CCaaLF (Concurrency Control as a Learnable Function), a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10036v3-abstract-full').style.display = 'inline'; document.getElementById('2503.10036v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10036v3-abstract-full" style="display: none;"> Concurrency control (CC) algorithms are important in modern transactional databases, as they enable high performance by executing transactions concurrently while ensuring correctness. However, state-of-the-art CC algorithms struggle to perform well across diverse workloads, and most do not consider workload drifts. In this paper, we propose CCaaLF (Concurrency Control as a Learnable Function), a novel learned concurrency control algorithm designed to achieve high performance across varying workloads. The algorithm is quick to optimize, making it robust against dynamic workloads. CCaaLF learns an agent function that captures a large number of design choices from existing CC algorithms. The function is implemented as an efficient in-database lookup table that maps database states to concurrency control actions. The learning process is based on a combination of Bayesian optimization and a novel graph reduction algorithm, which converges quickly to a function that achieves high transaction throughput. We compare CCaaLF against five state-of-the-art CC algorithms and show that our algorithm consistently outperforms them in terms of transaction throughput and optimization time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10036v3-abstract-full').style.display = 'none'; document.getElementById('2503.10036v3-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">v1</span> submitted 13 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">MSC Class:</span> 68P15 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.2.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.09663">arXiv:2503.09663</a> <span> [<a href="https://arxiv.org/pdf/2503.09663">pdf</a>, <a href="https://arxiv.org/format/2503.09663">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Operating Systems">cs.OS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> BYOS: Knowledge-driven Large Language Models Bring Your Own Operating System More Excellent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hongyu Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuchen Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+H">Haoran Luo</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+K">Kaichun Yao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Libo Zhang</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+M">Mingjie Xing</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanjun Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.09663v1-abstract-short" style="display: inline;"> Kernel configurations play an important role in the performance of Operating System (OS). However, with the rapid iteration of OS, finding the proper configurations that meet specific requirements can be challenging, which can be primarily attributed to the default kernel provided by vendors does not take the requirements of specific workloads into account, and the heavyweight tuning process canno… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09663v1-abstract-full').style.display = 'inline'; document.getElementById('2503.09663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09663v1-abstract-full" style="display: none;"> Kernel configurations play an important role in the performance of Operating System (OS). However, with the rapid iteration of OS, finding the proper configurations that meet specific requirements can be challenging, which can be primarily attributed to the default kernel provided by vendors does not take the requirements of specific workloads into account, and the heavyweight tuning process cannot catch up with the rapid evolving pace of the kernel. To address these challenges, we propose BYOS, a novel framework powered by Large Language Models (LLMs) to customize kernel configurations for diverse user requirements. By integrating OS-oriented Dual-layer Knowledge Graph (OD-KG) and corresponding reasoning strategy, BYOS enhanced the LLM's understanding of the characteristics and capabilities of OS, thus enabling customized, cost-effective, and convenient generation of kernel configurations. Experiments show that the kernels configured by BYOS outperform the default vendor-configured kernels by 7.1% to 155.4%, demonstrating the effectiveness and efficiency of BYOS in customizing kernel configurations. Our code is available at https://github.com/LHY-24/BYOS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09663v1-abstract-full').style.display = 'none'; document.getElementById('2503.09663v1-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> </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=Wu%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Wu%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