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 2,407 results for author: <span class="mathjax">Zhou, J</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=Zhou%2C+J">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="Zhou, J"> </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=Zhou%2C+J&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="Zhou, J"> <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=Zhou%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&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/2503.21463">arXiv:2503.21463</a> <span> [<a href="https://arxiv.org/pdf/2503.21463">pdf</a>, <a href="https://arxiv.org/format/2503.21463">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Unveiling Latent Information in Transaction Hashes: Hypergraph Learning for Ethereum Ponzi Scheme Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junhao Wu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yixin Yang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+C">Chengxiang Jin</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+S">Silu Mu</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+X">Xiaolei Qian</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiajun Zhou</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+S">Shanqing Yu</a>, <a href="/search/cs?searchtype=author&query=Xuan%2C+Q">Qi Xuan</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="2503.21463v1-abstract-short" style="display: inline;"> With the widespread adoption of Ethereum, financial frauds such as Ponzi schemes have become increasingly rampant in the blockchain ecosystem, posing significant threats to the security of account assets. Existing Ethereum fraud detection methods typically model account transactions as graphs, but this approach primarily focuses on binary transactional relationships between accounts, failing to ad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21463v1-abstract-full').style.display = 'inline'; document.getElementById('2503.21463v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.21463v1-abstract-full" style="display: none;"> With the widespread adoption of Ethereum, financial frauds such as Ponzi schemes have become increasingly rampant in the blockchain ecosystem, posing significant threats to the security of account assets. Existing Ethereum fraud detection methods typically model account transactions as graphs, but this approach primarily focuses on binary transactional relationships between accounts, failing to adequately capture the complex multi-party interaction patterns inherent in Ethereum. To address this, we propose a hypergraph modeling method for the Ponzi scheme detection method in Ethereum, called HyperDet. Specifically, we treat transaction hashes as hyperedges that connect all the relevant accounts involved in a transaction. Additionally, we design a two-step hypergraph sampling strategy to significantly reduce computational complexity. Furthermore, we introduce a dual-channel detection module, including the hypergraph detection channel and the hyper-homo graph detection channel, to be compatible with existing detection methods. Experimental results show that, compared to traditional homogeneous graph-based methods, the hyper-homo graph detection channel achieves significant performance improvements, demonstrating the superiority of hypergraph in Ponzi scheme detection. This research offers innovations for modeling complex relationships in blockchain data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21463v1-abstract-full').style.display = 'none'; document.getElementById('2503.21463v1-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/2503.21072">arXiv:2503.21072</a> <span> [<a href="https://arxiv.org/pdf/2503.21072">pdf</a>, <a href="https://arxiv.org/format/2503.21072">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"> HSLiNets: Evaluating Band Ordering Strategies in Hyperspectral and LiDAR Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J+X">Judy X Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jing Wang</a>, <a href="/search/cs?searchtype=author&query=Zhuanfeng"> Zhuanfeng</a>, <a href="/search/cs?searchtype=author&query=Li"> Li</a>, <a href="/search/cs?searchtype=author&query=Long%2C+C+S+Z">Chenhong Sui Zekun Long</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun 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="2503.21072v1-abstract-short" style="display: inline;"> The integration of hyperspectral imaging (HSI) and Light Detection and Ranging (LiDAR) data provides complementary spectral and spatial information for remote sensing applications. While previous studies have explored the role of band selection and grouping in HSI classification, little attention has been given to how the spectral sequence or band order affects classification outcomes when fused w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21072v1-abstract-full').style.display = 'inline'; document.getElementById('2503.21072v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.21072v1-abstract-full" style="display: none;"> The integration of hyperspectral imaging (HSI) and Light Detection and Ranging (LiDAR) data provides complementary spectral and spatial information for remote sensing applications. While previous studies have explored the role of band selection and grouping in HSI classification, little attention has been given to how the spectral sequence or band order affects classification outcomes when fused with LiDAR. In this work, we systematically investigate the influence of band order on HSI-LiDAR fusion performance. Through extensive experiments, we demonstrate that band order significantly impacts classification accuracy, revealing a previously overlooked factor in fusion-based models. Motivated by this observation, we propose a novel fusion architecture that not only integrates HSI and LiDAR data but also learns from multiple band order configurations. The proposed method enhances feature representation by adaptively fusing different spectral sequences, leading to improved classification accuracy. Experimental results on the Houston 2013 and Trento datasets show that our approach outperforms state-of-the-art fusion models. Data and code are available at https://github.com/Judyxyang/HSLiNets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.21072v1-abstract-full').style.display = 'none'; document.getElementById('2503.21072v1-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">2 figures, 5 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/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/2503.20981">arXiv:2503.20981</a> <span> [<a href="https://arxiv.org/pdf/2503.20981">pdf</a>, <a href="https://arxiv.org/format/2503.20981">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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfaction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiaoran Xu</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+Z">Zhaoqian Xue</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chi Zhang</a>, <a href="/search/cs?searchtype=author&query=Medri%2C+J">Jhonatan Medri</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Junjie Xiong</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiayan Zhou</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+J">Jin Jin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongfeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+S">Siyuan Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lingyao 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="2503.20981v1-abstract-short" style="display: inline;"> Investigating the public experience of urgent care facilities is essential for promoting community healthcare development. Traditional survey methods often fall short due to limited scope, time, and spatial coverage. Crowdsourcing through online reviews or social media offers a valuable approach to gaining such insights. With recent advancements in large language models (LLMs), extracting nuanced… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20981v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20981v1-abstract-full" style="display: none;"> Investigating the public experience of urgent care facilities is essential for promoting community healthcare development. Traditional survey methods often fall short due to limited scope, time, and spatial coverage. Crowdsourcing through online reviews or social media offers a valuable approach to gaining such insights. With recent advancements in large language models (LLMs), extracting nuanced perceptions from reviews has become feasible. This study collects Google Maps reviews across the DMV and Florida areas and conducts prompt engineering with the GPT model to analyze the aspect-based sentiment of urgent care. We first analyze the geospatial patterns of various aspects, including interpersonal factors, operational efficiency, technical quality, finances, and facilities. Next, we determine Census Block Group(CBG)-level characteristics underpinning differences in public perception, including population density, median income, GINI Index, rent-to-income ratio, household below poverty rate, no insurance rate, and unemployment rate. Our results show that interpersonal factors and operational efficiency emerge as the strongest determinants of patient satisfaction in urgent care, while technical quality, finances, and facilities show no significant independent effects when adjusted for in multivariate models. Among socioeconomic and demographic factors, only population density demonstrates a significant but modest association with patient ratings, while the remaining factors exhibit no significant correlations. Overall, this study highlights the potential of crowdsourcing to uncover the key factors that matter to residents and provide valuable insights for stakeholders to improve public satisfaction with urgent care. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20981v1-abstract-full').style.display = 'none'; document.getElementById('2503.20981v1-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/2503.20258">arXiv:2503.20258</a> <span> [<a href="https://arxiv.org/pdf/2503.20258">pdf</a>, <a href="https://arxiv.org/format/2503.20258">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"> Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiaheng Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yanfeng Zhou</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+W">Wei Fang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yuxing Tang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+L">Le Lu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Ge Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20258v1-abstract-short" style="display: inline;"> Ultrasound videos are an important form of clinical imaging data, and deep learning-based automated analysis can improve diagnostic accuracy and clinical efficiency. However, the scarcity of labeled data and the inherent challenges of video analysis have impeded the advancement of related methods. In this work, we introduce E-ViM$^3$, a data-efficient Vision Mamba network that preserves the 3D str… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20258v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20258v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20258v1-abstract-full" style="display: none;"> Ultrasound videos are an important form of clinical imaging data, and deep learning-based automated analysis can improve diagnostic accuracy and clinical efficiency. However, the scarcity of labeled data and the inherent challenges of video analysis have impeded the advancement of related methods. In this work, we introduce E-ViM$^3$, a data-efficient Vision Mamba network that preserves the 3D structure of video data, enhancing long-range dependencies and inductive biases to better model space-time correlations. With our design of Enclosure Global Tokens (EGT), the model captures and aggregates global features more effectively than competing methods. To further improve data efficiency, we employ masked video modeling for self-supervised pre-training, with the proposed Spatial-Temporal Chained (STC) masking strategy designed to adapt to various video scenarios. Experiments demonstrate that E-ViM$^3$ performs as the state-of-the-art in two high-level semantic analysis tasks across four datasets of varying sizes: EchoNet-Dynamic, CAMUS, MICCAI-BUV, and WHBUS. Furthermore, our model achieves competitive performance with limited labels, highlighting its potential impact on real-world clinical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20258v1-abstract-full').style.display = 'none'; document.getElementById('2503.20258v1-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/2503.20230">arXiv:2503.20230</a> <span> [<a href="https://arxiv.org/pdf/2503.20230">pdf</a>, <a href="https://arxiv.org/format/2503.20230">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> TraNCE: Transformative Non-linear Concept Explainer for CNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Akpudo%2C+U+E">Ugochukwu Ejike Akpudo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yongsheng Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Lewis%2C+A">Andrew Lewis</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="2503.20230v1-abstract-short" style="display: inline;"> Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models looked, concept-based explainability methods provide insights into what the models saw. However, their assumption of linear reconstructability of image activations fails to capture th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20230v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20230v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20230v1-abstract-full" style="display: none;"> Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models looked, concept-based explainability methods provide insights into what the models saw. However, their assumption of linear reconstructability of image activations fails to capture the intricate relationships within these activations. Their Fidelity-only approach to evaluating global explanations also presents a new concern. For the first time, we address these limitations with the novel Transformative Nonlinear Concept Explainer (TraNCE) for CNNs. Unlike linear reconstruction assumptions made by existing methods, TraNCE captures the intricate relationships within the activations. This study presents three original contributions to the CNN explainability literature: (i) An automatic concept discovery mechanism based on variational autoencoders (VAEs). This transformative concept discovery process enhances the identification of meaningful concepts from image activations. (ii) A visualization module that leverages the Bessel function to create a smooth transition between prototypical image pixels, revealing not only what the CNN saw but also what the CNN avoided, thereby mitigating the challenges of concept duplication as documented in previous works. (iii) A new metric, the Faith score, integrates both Coherence and Fidelity for a comprehensive evaluation of explainer faithfulness and consistency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20230v1-abstract-full').style.display = 'none'; document.getElementById('2503.20230v1-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/2503.20174">arXiv:2503.20174</a> <span> [<a href="https://arxiv.org/pdf/2503.20174">pdf</a>, <a href="https://arxiv.org/format/2503.20174">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"> Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shihao Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Dayu Li</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+J">Jinshan Pan</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Juncheng Zhou</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jinglei Shi</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jufeng Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20174v1-abstract-short" style="display: inline;"> Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from uniform split subspaces, and a redundancy issue is triggered to hinder the model from achieving satisfact… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20174v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20174v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20174v1-abstract-full" style="display: none;"> Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from uniform split subspaces, and a redundancy issue is triggered to hinder the model from achieving satisfactory outputs. In this paper, we propose to improve MHA by exploring diverse learners and introducing various interactions between heads, which results in a Hierarchical multI-head atteNtion driven Transformer model, termed HINT, for image restoration. HINT contains two modules, i.e., the Hierarchical Multi-Head Attention (HMHA) and the Query-Key Cache Updating (QKCU) module, to address the redundancy problem that is rooted in vanilla MHA. Specifically, HMHA extracts diverse contextual features by employing heads to learn from subspaces of varying sizes and containing different information. Moreover, QKCU, comprising intra- and inter-layer schemes, further reduces the redundancy problem by facilitating enhanced interactions between attention heads within and across layers. Extensive experiments are conducted on 12 benchmarks across 5 image restoration tasks, including low-light enhancement, dehazing, desnowing, denoising, and deraining, to demonstrate the superiority of HINT. The source code is available in the supplementary materials. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20174v1-abstract-full').style.display = 'none'; document.getElementById('2503.20174v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <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, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.19839">arXiv:2503.19839</a> <span> [<a href="https://arxiv.org/pdf/2503.19839">pdf</a>, <a href="https://arxiv.org/format/2503.19839">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"> FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiahao Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zunnan Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hanhui Li</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yiji Cheng</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+F">Fa-Ting Hong</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qin Lin</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Q">Qinglin Lu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xiaodan Liang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.19839v1-abstract-short" style="display: inline;"> Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1) complex scenarios; 2) semantic consistency; and 3) fine-grained editing. To address these issues, we propose FireEdit, an innovative Fine-grained Instruction-b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19839v1-abstract-full').style.display = 'inline'; document.getElementById('2503.19839v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.19839v1-abstract-full" style="display: none;"> Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1) complex scenarios; 2) semantic consistency; and 3) fine-grained editing. To address these issues, we propose FireEdit, an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM. FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process. Specifically, we enhance the fine-grained visual perception capabilities of the VLM by introducing additional region tokens. Relying solely on the output of the LLM to guide the diffusion model may lead to suboptimal editing results. Therefore, we propose a Time-Aware Target Injection module and a Hybrid Visual Cross Attention module. The former dynamically adjusts the guidance strength at various denoising stages by integrating timestep embeddings with the text embeddings. The latter enhances visual details for image editing, thereby preserving semantic consistency between the edited result and the source image. By combining the VLM enhanced with fine-grained region tokens and the time-dependent diffusion model, FireEdit demonstrates significant advantages in comprehending editing instructions and maintaining high semantic consistency. Extensive experiments indicate that our approach surpasses the state-of-the-art instruction-based image editing methods. Our project is available at https://zjgans.github.io/fireedit.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19839v1-abstract-full').style.display = 'none'; document.getElementById('2503.19839v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <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/2503.19574">arXiv:2503.19574</a> <span> [<a href="https://arxiv.org/pdf/2503.19574">pdf</a>, <a href="https://arxiv.org/format/2503.19574">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Context-Efficient Retrieval with Factual Decomposition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yanhong Li</a>, <a href="/search/cs?searchtype=author&query=Yunis%2C+D">David Yunis</a>, <a href="/search/cs?searchtype=author&query=McAllester%2C+D">David McAllester</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiawei 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="2503.19574v1-abstract-short" style="display: inline;"> There has recently been considerable interest in incorporating information retrieval into large language models (LLMs). Retrieval from a dynamically expanding external corpus of text allows a model to incorporate current events and can be viewed as a form of episodic memory. Here we demonstrate that pre-processing the external corpus into semi-structured ''atomic facts'' makes retrieval more effic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19574v1-abstract-full').style.display = 'inline'; document.getElementById('2503.19574v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.19574v1-abstract-full" style="display: none;"> There has recently been considerable interest in incorporating information retrieval into large language models (LLMs). Retrieval from a dynamically expanding external corpus of text allows a model to incorporate current events and can be viewed as a form of episodic memory. Here we demonstrate that pre-processing the external corpus into semi-structured ''atomic facts'' makes retrieval more efficient. More specifically, we demonstrate that our particular form of atomic facts improves performance on various question answering tasks when the amount of retrieved text is limited. Limiting the amount of retrieval reduces the size of the context and improves inference efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19574v1-abstract-full').style.display = 'none'; document.getElementById('2503.19574v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <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">NAACL 2025 Main Conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.19506">arXiv:2503.19506</a> <span> [<a href="https://arxiv.org/pdf/2503.19506">pdf</a>, <a href="https://arxiv.org/format/2503.19506">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TIV.2024.3414852">10.1109/TIV.2024.3414852 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MM-LINS: a Multi-Map LiDAR-Inertial System for Over-Degenerate Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+Y">Yongxin Ma</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jie Xu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shenghai Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhi%2C+T">Tian Zhi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+W">Wenlu Yu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+L">Lihua 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="2503.19506v1-abstract-short" style="display: inline;"> SLAM plays a crucial role in automation tasks, such as warehouse logistics, healthcare robotics, and restaurant delivery. These scenes come with various challenges, including navigating around crowds of people, dealing with flying plastic bags that can temporarily blind sensors, and addressing reduced LiDAR density caused by cooking smoke. Such scenarios can result in over-degeneracy, causing the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19506v1-abstract-full').style.display = 'inline'; document.getElementById('2503.19506v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.19506v1-abstract-full" style="display: none;"> SLAM plays a crucial role in automation tasks, such as warehouse logistics, healthcare robotics, and restaurant delivery. These scenes come with various challenges, including navigating around crowds of people, dealing with flying plastic bags that can temporarily blind sensors, and addressing reduced LiDAR density caused by cooking smoke. Such scenarios can result in over-degeneracy, causing the map to drift. To address this issue, this paper presents a multi-map LiDAR-inertial system (MM-LINS) for the first time. The front-end employs an iterated error state Kalman filter for state estimation and introduces a reliable evaluation strategy for degeneracy detection. If over-degeneracy is detected, the active map will be stored into sleeping maps. Subsequently, the system continuously attempts to construct new maps using a dynamic initialization method to ensure successful initialization upon leaving the over-degeneracy. Regarding the back-end, the Scan Context descriptor is utilized to detect inter-map similarity. Upon successful recognition of a sleeping map that shares a common region with the active map, the overlapping trajectory region is utilized to constrain the positional transformation near the edge of the prior map. In response to this, a constraint-enhanced map fusion strategy is proposed to achieve high-precision positional and mapping results. Experiments have been conducted separately on both public datasets that exhibited over-degenerate conditions and in real-world environments. These tests demonstrated the effectiveness of MM-LINS in over-degeneracy environment. Our codes are open-sourced on Github. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19506v1-abstract-full').style.display = 'none'; document.getElementById('2503.19506v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <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 Intelligent Vehicles</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.19041">arXiv:2503.19041</a> <span> [<a href="https://arxiv.org/pdf/2503.19041">pdf</a>, <a href="https://arxiv.org/format/2503.19041">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> LookAhead Tuning: Safer Language Models via Partial Answer Previews </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kangwei Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mengru Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yujie Luo</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+L">Lin Yuan</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+M">Mengshu Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+N">Ningyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+L">Lei Liang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhiqiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Huajun Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.19041v1-abstract-short" style="display: inline;"> Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often undermines their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead Tuning, which comprises two simple, low-resource, and effective data-driven methods that modify training data by previewing partial answer prefixes. Both methods aim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19041v1-abstract-full').style.display = 'inline'; document.getElementById('2503.19041v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.19041v1-abstract-full" style="display: none;"> Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often undermines their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead Tuning, which comprises two simple, low-resource, and effective data-driven methods that modify training data by previewing partial answer prefixes. Both methods aim to preserve the model's inherent safety mechanisms by minimizing perturbations to initial token distributions. Comprehensive experiments demonstrate that LookAhead Tuning effectively maintains model safety without sacrificing robust performance on downstream tasks. Our findings position LookAhead Tuning as a reliable and efficient solution for the safe and effective adaptation of LLMs. Code is released at https://github.com/zjunlp/LookAheadTuning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.19041v1-abstract-full').style.display = 'none'; document.getElementById('2503.19041v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18945">arXiv:2503.18945</a> <span> [<a href="https://arxiv.org/pdf/2503.18945">pdf</a>, <a href="https://arxiv.org/format/2503.18945">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <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"> Aether: Geometric-Aware Unified World Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aether+Team"> Aether Team</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Haoyi Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jianjun Zhou</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+W">Wenzheng Chang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zizun Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junyi Chen</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chunhua Shen</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+J">Jiangmiao Pang</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tong He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18945v2-abstract-short" style="display: inline;"> The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper proposes Aether, a unified framework that enables geometry-aware reasoning in world models by jointly optimizing three core capabilities: (1) 4D dynamic reconstruction, (2) action-conditioned video prediction, and (3) goal-con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18945v2-abstract-full').style.display = 'inline'; document.getElementById('2503.18945v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18945v2-abstract-full" style="display: none;"> The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper proposes Aether, a unified framework that enables geometry-aware reasoning in world models by jointly optimizing three core capabilities: (1) 4D dynamic reconstruction, (2) action-conditioned video prediction, and (3) goal-conditioned visual planning. Through task-interleaved feature learning, Aether achieves synergistic knowledge sharing across reconstruction, prediction, and planning objectives. Building upon video generation models, our framework demonstrates unprecedented synthetic-to-real generalization despite never observing real-world data during training. Furthermore, our approach achieves zero-shot generalization in both action following and reconstruction tasks, thanks to its intrinsic geometric modeling. Remarkably, even without real-world data, its reconstruction performance is comparable with or even better than that of domain-specific models. Additionally, Aether employs camera trajectories as geometry-informed action spaces, enabling effective action-conditioned prediction and visual planning. We hope our work inspires the community to explore new frontiers in physically-reasonable world modeling and its applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18945v2-abstract-full').style.display = 'none'; document.getElementById('2503.18945v2-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 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project Page: https://aether-world.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/2503.18860">arXiv:2503.18860</a> <span> [<a href="https://arxiv.org/pdf/2503.18860">pdf</a>, <a href="https://arxiv.org/format/2503.18860">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"> HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zunnan Xu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhentao Yu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zixiang Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+X">Xiaoyu Jin</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+F">Fa-Ting Hong</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+X">Xiaozhong Ji</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Junwei Zhu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+C">Chengfei Cai</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+S">Shiyu Tang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qin Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiu Li</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Q">Qinglin Lu</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="2503.18860v2-abstract-short" style="display: inline;"> We introduce HunyuanPortrait, a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation. Given a single portrait image as an appearance reference and video clips as driving templates, HunyuanPortrait can animate the character in the reference image by the facial expression and head pose of the driving videos. In our fra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18860v2-abstract-full').style.display = 'inline'; document.getElementById('2503.18860v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18860v2-abstract-full" style="display: none;"> We introduce HunyuanPortrait, a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation. Given a single portrait image as an appearance reference and video clips as driving templates, HunyuanPortrait can animate the character in the reference image by the facial expression and head pose of the driving videos. In our framework, we utilize pre-trained encoders to achieve the decoupling of portrait motion information and identity in videos. To do so, implicit representation is adopted to encode motion information and is employed as control signals in the animation phase. By leveraging the power of stable video diffusion as the main building block, we carefully design adapter layers to inject control signals into the denoising unet through attention mechanisms. These bring spatial richness of details and temporal consistency. HunyuanPortrait also exhibits strong generalization performance, which can effectively disentangle appearance and motion under different image styles. Our framework outperforms existing methods, demonstrating superior temporal consistency and controllability. Our project is available at https://kkakkkka.github.io/HunyuanPortrait. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18860v2-abstract-full').style.display = 'none'; document.getElementById('2503.18860v2-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 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/2503.18432">arXiv:2503.18432</a> <span> [<a href="https://arxiv.org/pdf/2503.18432">pdf</a>, <a href="https://arxiv.org/format/2503.18432">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Junsong Li</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yutao Yang</a>, <a href="/search/cs?searchtype=author&query=Zhan%2C+B">Bihao Zhan</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+Q">Qianjun Pan</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yuyang Ding</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qin Chen</a>, <a href="/search/cs?searchtype=author&query=Bo%2C+J">Jiang Bo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+X">Xin Lin</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Liang He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18432v1-abstract-short" style="display: inline;"> Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement lea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18432v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18432v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18432v1-abstract-full" style="display: none;"> Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC. Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs. Then, we design a space-constrained policy network to improve the stability of RL. Then, we introduce a fine-grained reward network to convert the binary human feedback into a continuous value. We conduct extensive experiments over two benchmark datasets and the results show that our model outperforms the eleven strong baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18432v1-abstract-full').style.display = 'none'; document.getElementById('2503.18432v1-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/2503.18361">arXiv:2503.18361</a> <span> [<a href="https://arxiv.org/pdf/2503.18361">pdf</a>, <a href="https://arxiv.org/format/2503.18361">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"> NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+E+Y">Emily Yue-ting Jia</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Junsheng Zhou</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+B">Baorui Ma</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+K">Kanle Shi</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yu-Shen 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="2503.18361v1-abstract-short" style="display: inline;"> Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues without considering the importance of color. In this paper, we present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18361v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18361v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18361v1-abstract-full" style="display: none;"> Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues without considering the importance of color. In this paper, we present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using volume rendering for surface reconstruction. Our NeRF prior can provide both geometric and color clues, and also get trained fast under the same scene without additional data. Based on the NeRF prior, we are enabled to learn a signed distance function (SDF) by explicitly imposing a multi-view consistency constraint on each ray intersection for surface inference. Specifically, at each ray intersection, we use the density in the prior as a coarse geometry estimation, while using the color near the surface as a clue to check its visibility from another view angle. For the textureless areas where the multi-view consistency constraint does not work well, we further introduce a depth consistency loss with confidence weights to infer the SDF. Our experimental results outperform the state-of-the-art methods under the widely used benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18361v1-abstract-full').style.display = 'none'; document.getElementById('2503.18361v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by CVPR 2025. Project page: https://wen-yuan-zhang.github.io/NeRFPrior/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18100">arXiv:2503.18100</a> <span> [<a href="https://arxiv.org/pdf/2503.18100">pdf</a>, <a href="https://arxiv.org/format/2503.18100">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"> M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuesong Chen</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+S">Shaoshuai Shi</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+T">Tao Ma</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingqiu Zhou</a>, <a href="/search/cs?searchtype=author&query=See%2C+S">Simon See</a>, <a href="/search/cs?searchtype=author&query=Cheung%2C+K+C">Ka Chun Cheung</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongsheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18100v1-abstract-short" style="display: inline;"> The perception system for autonomous driving generally requires to handle multiple diverse sub-tasks. However, current algorithms typically tackle individual sub-tasks separately, which leads to low efficiency when aiming at obtaining full-perception results. Some multi-task learning methods try to unify multiple tasks with one model, but do not solve the conflicts in multi-task learning. In this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18100v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18100v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18100v1-abstract-full" style="display: none;"> The perception system for autonomous driving generally requires to handle multiple diverse sub-tasks. However, current algorithms typically tackle individual sub-tasks separately, which leads to low efficiency when aiming at obtaining full-perception results. Some multi-task learning methods try to unify multiple tasks with one model, but do not solve the conflicts in multi-task learning. In this paper, we introduce M3Net, a novel multimodal and multi-task network that simultaneously tackles detection, segmentation, and 3D occupancy prediction for autonomous driving and achieves superior performance than single task model. M3Net takes multimodal data as input and multiple tasks via query-token interactions. To enhance the integration of multi-modal features for multi-task learning, we first propose the Modality-Adaptive Feature Integration (MAFI) module, which enables single-modality features to predict channel-wise attention weights for their high-performing tasks, respectively. Based on integrated features, we then develop task-specific query initialization strategies to accommodate the needs of detection/segmentation and 3D occupancy prediction. Leveraging the properly initialized queries, a shared decoder transforms queries and BEV features layer-wise, facilitating multi-task learning. Furthermore, we propose a Task-oriented Channel Scaling (TCS) module in the decoder to mitigate conflicts between optimizing for different tasks. Additionally, our proposed multi-task querying and TCS module support both Transformer-based decoder and Mamba-based decoder, demonstrating its flexibility to different architectures. M3Net achieves state-of-the-art multi-task learning performance on the nuScenes benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18100v1-abstract-full').style.display = 'none'; document.getElementById('2503.18100v1-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 AAAI 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/2503.17915">arXiv:2503.17915</a> <span> [<a href="https://arxiv.org/pdf/2503.17915">pdf</a>, <a href="https://arxiv.org/format/2503.17915">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Cat-AIR: Content and Task-Aware All-in-One Image Restoration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jiachen Jiang</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+T">Tianyu Ding</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Ke Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jinxin Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tianyi Chen</a>, <a href="/search/cs?searchtype=author&query=Zharkov%2C+I">Ilya Zharkov</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhihui Zhu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+L">Luming Liang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.17915v1-abstract-short" style="display: inline;"> All-in-one image restoration seeks to recover high-quality images from various types of degradation using a single model, without prior knowledge of the corruption source. However, existing methods often struggle to effectively and efficiently handle multiple degradation types. We present Cat-AIR, a novel \textbf{C}ontent \textbf{A}nd \textbf{T}ask-aware framework for \textbf{A}ll-in-one \textbf{I… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17915v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17915v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17915v1-abstract-full" style="display: none;"> All-in-one image restoration seeks to recover high-quality images from various types of degradation using a single model, without prior knowledge of the corruption source. However, existing methods often struggle to effectively and efficiently handle multiple degradation types. We present Cat-AIR, a novel \textbf{C}ontent \textbf{A}nd \textbf{T}ask-aware framework for \textbf{A}ll-in-one \textbf{I}mage \textbf{R}estoration. Cat-AIR incorporates an alternating spatial-channel attention mechanism that adaptively balances the local and global information for different tasks. Specifically, we introduce cross-layer channel attentions and cross-feature spatial attentions that allocate computations based on content and task complexity. Furthermore, we propose a smooth learning strategy that allows for seamless adaptation to new restoration tasks while maintaining performance on existing ones. Extensive experiments demonstrate that Cat-AIR achieves state-of-the-art results across a wide range of restoration tasks, requiring fewer FLOPs than previous methods, establishing new benchmarks for efficient all-in-one image restoration. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17915v1-abstract-full').style.display = 'none'; document.getElementById('2503.17915v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17793">arXiv:2503.17793</a> <span> [<a href="https://arxiv.org/pdf/2503.17793">pdf</a>, <a href="https://arxiv.org/format/2503.17793">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"> Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Codefuse"> Codefuse</a>, <a href="/search/cs?searchtype=author&query=Team%2C+L">Ling Team</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+W">Wenting Cai</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuchen Cao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chaoyu Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Siba Chen</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Q">Qing Cui</a>, <a href="/search/cs?searchtype=author&query=Di%2C+P">Peng Di</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Junpeng Fang</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+Z">Zi Gong</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+T">Ting Guo</a>, <a href="/search/cs?searchtype=author&query=He%2C+Z">Zhengyu He</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yang Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Cong Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jianguo Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zheng Li</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+S">Shijie Lian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">BingChang Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Songshan Luo</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+S">Shuo Mao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+M">Min Shen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jian Wu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiaolong Yang</a> , et al. (8 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="2503.17793v1-abstract-short" style="display: inline;"> Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the Deep… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17793v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17793v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17793v1-abstract-full" style="display: none;"> Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{https://huggingface.co/inclusionAI/Ling-Coder-lite}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17793v1-abstract-full').style.display = 'none'; document.getElementById('2503.17793v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17735">arXiv:2503.17735</a> <span> [<a href="https://arxiv.org/pdf/2503.17735">pdf</a>, <a href="https://arxiv.org/format/2503.17735">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"> RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+Z">Zhiqiang Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Ting Zhang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Ying Deng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiapei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yeshuang Zhu</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+Z">Zexi Jia</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jinchao 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="2503.17735v1-abstract-short" style="display: inline;"> Recently, great progress has been made in video generation technology, attracting the widespread attention of scholars. To apply this technology to downstream applications under resource-constrained conditions, researchers usually fine-tune the pre-trained models based on parameter-efficient tuning methods such as Adapter or Lora. Although these methods can transfer the knowledge from the source d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17735v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17735v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17735v1-abstract-full" style="display: none;"> Recently, great progress has been made in video generation technology, attracting the widespread attention of scholars. To apply this technology to downstream applications under resource-constrained conditions, researchers usually fine-tune the pre-trained models based on parameter-efficient tuning methods such as Adapter or Lora. Although these methods can transfer the knowledge from the source domain to the target domain, fewer training parameters lead to poor fitting ability, and the knowledge from the source domain may lead to the inference process deviating from the target domain. In this paper, we argue that under constrained resources, training a smaller video generation model from scratch using only million-level samples can outperform parameter-efficient tuning on larger models in downstream applications: the core lies in the effective utilization of data and curriculum strategy. Take animated sticker generation (ASG) as a case study, we first construct a discrete frame generation network for stickers with low frame rates, ensuring that its parameters meet the requirements of model training under constrained resources. In order to provide data support for models trained from scratch, we come up with a dual-mask based data utilization strategy, which manages to improve the availability and expand the diversity of limited data. To facilitate convergence under dual-mask situation, we propose a difficulty-adaptive curriculum learning method, which decomposes the sample entropy into static and adaptive components so as to obtain samples from easy to difficult. The experiment demonstrates that our resource-efficient dual-mask training framework is quantitatively and qualitatively superior to efficient-parameter tuning methods such as I2V-Adapter and SimDA, verifying the feasibility of our method on downstream tasks under constrained resources. Code will be available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17735v1-abstract-full').style.display = 'none'; document.getElementById('2503.17735v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17682">arXiv:2503.17682</a> <span> [<a href="https://arxiv.org/pdf/2503.17682">pdf</a>, <a href="https://arxiv.org/format/2503.17682">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ji%2C+J">Jiaming Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyu Chen</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+R">Rui Pan</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Han Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Conghui Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiahao Li</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+D">Donghai Hong</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+B">Boyuan Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiayi Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kaile Wang</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+J">Juntao Dai</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+C">Chi-Min Chan</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S">Sirui Han</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Yike Guo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yaodong Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.17682v1-abstract-short" style="display: inline;"> Multimodal large language models (MLLMs) are critical for developing general-purpose AI assistants, yet they face growing safety risks. How can we ensure that MLLMs are safely aligned to prevent undesired behaviors such as discrimination, misinformation, or violations of ethical standards? In a further step, we need to explore how to fine-tune MLLMs to enhance reasoning performance while ensuring… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17682v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17682v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17682v1-abstract-full" style="display: none;"> Multimodal large language models (MLLMs) are critical for developing general-purpose AI assistants, yet they face growing safety risks. How can we ensure that MLLMs are safely aligned to prevent undesired behaviors such as discrimination, misinformation, or violations of ethical standards? In a further step, we need to explore how to fine-tune MLLMs to enhance reasoning performance while ensuring they satisfy safety constraints. Fundamentally, this can be formulated as a min-max optimization problem. In this study, we propose Safe RLHF-V, the first multimodal safety alignment framework that jointly optimizes helpfulness and safety using separate multimodal reward and cost models within a Lagrangian-based constrained optimization framework. Given that there is a lack of preference datasets that separate helpfulness and safety in multimodal scenarios, we introduce BeaverTails-V, the first open-source dataset with dual preference annotations for helpfulness and safety, along with multi-level safety labels (minor, moderate, severe). Additionally, we design a Multi-level Guardrail System to proactively defend against unsafe queries and adversarial attacks. By applying the Beaver-Guard-V moderation for 5 rounds of filtering and re-generation on the precursor model, the overall safety of the upstream model is significantly improved by an average of 40.9%. Experimental results demonstrate that fine-tuning different MLLMs with Safe RLHF can effectively enhance model helpfulness while ensuring improved safety. Specifically, Safe RLHF-V improves model safety by 34.2% and helpfulness by 34.3%. All of datasets, models, and code can be found at https://github.com/SafeRLHF-V to support the safety development of MLLMs and reduce potential societal risks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17682v1-abstract-full').style.display = 'none'; document.getElementById('2503.17682v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17195">arXiv:2503.17195</a> <span> [<a href="https://arxiv.org/pdf/2503.17195">pdf</a>, <a href="https://arxiv.org/format/2503.17195">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sheng Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Pengan Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingqi Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qintong Li</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Jingwei Dong</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+J">Jiahui Gao</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+B">Boyang Xue</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jiyue Jiang</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+L">Lingpeng Kong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+C">Chuan 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="2503.17195v1-abstract-short" style="display: inline;"> Model customization requires high-quality and diverse datasets, but acquiring such data remains challenging and costly. Although large language models (LLMs) can synthesize training data, current approaches are constrained by limited seed data, model bias and insufficient control over the generation process, resulting in limited diversity and biased distribution with the increase of data scales. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17195v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17195v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17195v1-abstract-full" style="display: none;"> Model customization requires high-quality and diverse datasets, but acquiring such data remains challenging and costly. Although large language models (LLMs) can synthesize training data, current approaches are constrained by limited seed data, model bias and insufficient control over the generation process, resulting in limited diversity and biased distribution with the increase of data scales. To tackle this challenge, we present TreeSynth, a tree-guided subspace-based data synthesis framework that recursively partitions the entire data space into hierar-chical subspaces, enabling comprehensive and diverse scaling of data synthesis. Briefly, given a task-specific description, we construct a data space partitioning tree by iteratively executing criteria determination and subspace coverage steps. This hierarchically divides the whole space (i.e., root node) into mutually exclusive and complementary atomic subspaces (i.e., leaf nodes). By collecting synthesized data according to the attributes of each leaf node, we obtain a diverse dataset that fully covers the data space. Empirically, our extensive experiments demonstrate that TreeSynth surpasses both human-designed datasets and the state-of-the-art data synthesis baselines, achieving maximum improvements of 45.2% in data diversity and 17.6% in downstream task performance across various models and tasks. Hopefully, TreeSynth provides a scalable solution to synthesize diverse and comprehensive datasets from scratch without human intervention. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17195v1-abstract-full').style.display = 'none'; document.getElementById('2503.17195v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17155">arXiv:2503.17155</a> <span> [<a href="https://arxiv.org/pdf/2503.17155">pdf</a>, <a href="https://arxiv.org/format/2503.17155">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"> D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+P">Panpan Wang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Liqiang Niu</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+F">Fandong Meng</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jinan Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yufeng Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie 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="2503.17155v1-abstract-short" style="display: inline;"> In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of scalability and flexibility embrace a discrete-valued tokenizer, but face the challenge of poor image generation quality. In contrast, diffusion models take advantage… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17155v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17155v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17155v1-abstract-full" style="display: none;"> In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of scalability and flexibility embrace a discrete-valued tokenizer, but face the challenge of poor image generation quality. In contrast, diffusion models take advantage of the continuous-valued tokenizer to achieve better generation quality but are subject to low efficiency and complexity. The existing hybrid models are mainly to compensate for information loss and simplify the diffusion learning process. The potential of merging discrete-valued and continuous-valued tokens in the field of image generation has not yet been explored. In this paper, we propose D2C, a novel two-stage method to enhance model generation capacity. In the first stage, the discrete-valued tokens representing coarse-grained image features are sampled by employing a small discrete-valued generator. Then in the second stage, the continuous-valued tokens representing fine-grained image features are learned conditioned on the discrete token sequence. In addition, we design two kinds of fusion modules for seamless interaction. On the ImageNet-256 benchmark, extensive experiment results validate that our model achieves superior performance compared with several continuous-valued and discrete-valued generative models on the class-conditional image generation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17155v1-abstract-full').style.display = 'none'; document.getElementById('2503.17155v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.16578">arXiv:2503.16578</a> <span> [<a href="https://arxiv.org/pdf/2503.16578">pdf</a>, <a href="https://arxiv.org/format/2503.16578">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="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"> SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hui Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shiyao Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junyang Chen</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jiabei He</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiaming Zhou</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xi Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yequan Wang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yonghua Lin</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+Y">Yong Qin</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="2503.16578v1-abstract-short" style="display: inline;"> While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16578v1-abstract-full').style.display = 'inline'; document.getElementById('2503.16578v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16578v1-abstract-full" style="display: none;"> While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions, exacerbates this issue. To address the critical scarcity of speech data from individuals aged 75 and above, we introduce SeniorTalk, a carefully annotated Chinese spoken dialogue dataset. This dataset contains 55.53 hours of speech from 101 natural conversations involving 202 participants, ensuring a strategic balance across gender, region, and age. Through detailed annotation across multiple dimensions, it can support a wide range of speech tasks. We perform extensive experiments on speaker verification, speaker diarization, speech recognition, and speech editing tasks, offering crucial insights for the development of speech technologies targeting this age group. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16578v1-abstract-full').style.display = 'none'; document.getElementById('2503.16578v1-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/2503.15973">arXiv:2503.15973</a> <span> [<a href="https://arxiv.org/pdf/2503.15973">pdf</a>, <a href="https://arxiv.org/format/2503.15973">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"> STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zichen Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+K">Kunlun Xu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+B">Bing Su</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+X">Xu Zou</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Y">Yuxin Peng</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiahuan 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="2503.15973v2-abstract-short" style="display: inline;"> Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15973v2-abstract-full').style.display = 'inline'; document.getElementById('2503.15973v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15973v2-abstract-full" style="display: none;"> Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts, but they typically rely on a single static prompt for all video sequences, overlooking the diverse temporal dynamics and spatial variations that exist across frames. This limitation significantly hinders the model's ability to capture essential temporal information for effective video understanding. To address this, we propose an integrated Spatial-TempOral dynamic Prompting (STOP) model which consists of two complementary modules, the intra-frame spatial prompting and inter-frame temporal prompting. Our intra-frame spatial prompts are designed to adaptively highlight discriminative regions within each frame by leveraging intra-frame attention and temporal variation, allowing the model to focus on areas with substantial temporal dynamics and capture fine-grained spatial details. Additionally, to highlight the varying importance of frames for video understanding, we further introduce inter-frame temporal prompts, dynamically inserting prompts between frames with high temporal variance as measured by frame similarity. This enables the model to prioritize key frames and enhances its capacity to understand temporal dependencies across sequences. Extensive experiments on various video benchmarks demonstrate that STOP consistently achieves superior performance against state-of-the-art methods. The code is available at https://github.com/zhoujiahuan1991/CVPR2025-STOP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15973v2-abstract-full').style.display = 'none'; document.getElementById('2503.15973v2-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">v1</span> submitted 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/2503.15898">arXiv:2503.15898</a> <span> [<a href="https://arxiv.org/pdf/2503.15898">pdf</a>, <a href="https://arxiv.org/format/2503.15898">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"> Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wen%2C+B">Boran Wen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+D">Dingbang Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zichen Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiahong Zhou</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+J">Jianbin Deng</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+J">Jingyu Gong</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yulong Chen</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+L">Lizhuang Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yong-Lu 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="2503.15898v1-abstract-short" style="display: inline;"> Reconstructing human-object interactions (HOI) from single images is fundamental in computer vision. Existing methods are primarily trained and tested on indoor scenes due to the lack of 3D data, particularly constrained by the object variety, making it challenging to generalize to real-world scenes with a wide range of objects. The limitations of previous 3D HOI datasets were primarily due to the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15898v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15898v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15898v1-abstract-full" style="display: none;"> Reconstructing human-object interactions (HOI) from single images is fundamental in computer vision. Existing methods are primarily trained and tested on indoor scenes due to the lack of 3D data, particularly constrained by the object variety, making it challenging to generalize to real-world scenes with a wide range of objects. The limitations of previous 3D HOI datasets were primarily due to the difficulty in acquiring 3D object assets. However, with the development of 3D reconstruction from single images, recently it has become possible to reconstruct various objects from 2D HOI images. We therefore propose a pipeline for annotating fine-grained 3D humans, objects, and their interactions from single images. We annotated 2.5k+ 3D HOI assets from existing 2D HOI datasets and built the first open-vocabulary in-the-wild 3D HOI dataset Open3DHOI, to serve as a future test set. Moreover, we design a novel Gaussian-HOI optimizer, which efficiently reconstructs the spatial interactions between humans and objects while learning the contact regions. Besides the 3D HOI reconstruction, we also propose several new tasks for 3D HOI understanding to pave the way for future work. Data and code will be publicly available at https://wenboran2002.github.io/3dhoi. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15898v1-abstract-full').style.display = 'none'; document.getElementById('2503.15898v1-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">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/2503.15809">arXiv:2503.15809</a> <span> [<a href="https://arxiv.org/pdf/2503.15809">pdf</a>, <a href="https://arxiv.org/format/2503.15809">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Controlling Avatar Diffusion with Learnable Gaussian Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xuan Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingtao Zhou</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+D">Dongyu Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yuqi Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Juyong 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="2503.15809v1-abstract-short" style="display: inline;"> Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal coherence, and motion accuracy. A key reason for these shortcomings is the limited representation ability of commonly used control signals(e.g., landmarks, depth maps, etc.). In addition, the lack of diversity in identity… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15809v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15809v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15809v1-abstract-full" style="display: none;"> Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal coherence, and motion accuracy. A key reason for these shortcomings is the limited representation ability of commonly used control signals(e.g., landmarks, depth maps, etc.). In addition, the lack of diversity in identity and pose variations in public datasets further hinders progress in this area. In this paper, we analyze the shortcomings of current control signals and introduce a novel control signal representation that is optimizable, dense, expressive, and 3D consistent. Our method embeds a learnable neural Gaussian onto a parametric head surface, which greatly enhances the consistency and expressiveness of diffusion-based head models. Regarding the dataset, we synthesize a large-scale dataset with multiple poses and identities. In addition, we use real/synthetic labels to effectively distinguish real and synthetic data, minimizing the impact of imperfections in synthetic data on the generated head images. Extensive experiments show that our model outperforms existing methods in terms of realism, expressiveness, and 3D consistency. Our code, synthetic datasets, and pre-trained models will be released in our project page: https://ustc3dv.github.io/Learn2Control/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15809v1-abstract-full').style.display = 'none'; document.getElementById('2503.15809v1-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">Project Page: https://ustc3dv.github.io/Learn2Control/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15369">arXiv:2503.15369</a> <span> [<a href="https://arxiv.org/pdf/2503.15369">pdf</a>, <a href="https://arxiv.org/format/2503.15369">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"> EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yinan Liang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Ziwei Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiuwei Xu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiwen Lu</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="2503.15369v1-abstract-short" style="display: inline;"> While multimodal large language models demonstrate strong performance in complex reasoning tasks, they pose significant challenges related to model complexity during deployment, especially for resource-limited devices. In this paper, we propose an automatic pruning method for large vision-language models to enhance the efficiency of multimodal reasoning. Conventional methods rely on the training d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15369v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15369v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15369v1-abstract-full" style="display: none;"> While multimodal large language models demonstrate strong performance in complex reasoning tasks, they pose significant challenges related to model complexity during deployment, especially for resource-limited devices. In this paper, we propose an automatic pruning method for large vision-language models to enhance the efficiency of multimodal reasoning. Conventional methods rely on the training data of the original model to select the proper pruning ratio for different network components. However, these methods are impractical for large vision-language models due to the unaffordable search costs caused by web-scale training corpus. In contrast, our approach only leverages a small number of samples to search for the desired pruning policy by maximizing its generalization ability on unknown training data while maintaining the model accuracy, which enables the achievement of an optimal trade-off between accuracy and efficiency for large visual language models. Specifically, we formulate the generalization gap of the pruning strategy using the structural risk minimization principle. Based on both task performance and generalization capability, we iteratively search for the optimal pruning policy within a given search space and optimize the vision projector to evolve the search space with higher upper bound of performance. We conduct extensive experiments on the ScienceQA, Vizwiz, MM-vet, and LLaVA-Bench datasets for the task of visual question answering. Using only 64 samples for pruning policy search, EfficientLLaVA achieves an accuracy of 83.05% on ScienceQA, along with a $\times$ 1.8 speedup compared to the dense LLaVA-v1.5-7B model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15369v1-abstract-full').style.display = 'none'; document.getElementById('2503.15369v1-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">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/2503.14919">arXiv:2503.14919</a> <span> [<a href="https://arxiv.org/pdf/2503.14919">pdf</a>, <a href="https://arxiv.org/format/2503.14919">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"> GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+J">Junyu Shi</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lijiang Liu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yong Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhiyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jinni Zhou</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+Q">Qiang Nie</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="2503.14919v1-abstract-short" style="display: inline;"> Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due to variations in motion content. To address this, we propose Generative Pretrained Multi-path Motion Model (GenM$^3$), a comprehensive framework designed to learn unified motion representations. GenM$^3$ comprises two c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14919v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14919v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14919v1-abstract-full" style="display: none;"> Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due to variations in motion content. To address this, we propose Generative Pretrained Multi-path Motion Model (GenM$^3$), a comprehensive framework designed to learn unified motion representations. GenM$^3$ comprises two components: 1) a Multi-Expert VQ-VAE (MEVQ-VAE) that adapts to different dataset distributions to learn a unified discrete motion representation, and 2) a Multi-path Motion Transformer (MMT) that improves intra-modal representations by using separate modality-specific pathways, each with densely activated experts to accommodate variations within that modality, and improves inter-modal alignment by the text-motion shared pathway. To enable large-scale training, we integrate and unify 11 high-quality motion datasets (approximately 220 hours of motion data) and augment it with textual annotations (nearly 10,000 motion sequences labeled by a large language model and 300+ by human experts). After training on our integrated dataset, GenM$^3$ achieves a state-of-the-art FID of 0.035 on the HumanML3D benchmark, surpassing state-of-the-art methods by a large margin. It also demonstrates strong zero-shot generalization on IDEA400 dataset, highlighting its effectiveness and adaptability across diverse motion scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14919v1-abstract-full').style.display = 'none'; document.getElementById('2503.14919v1-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/2503.14917">arXiv:2503.14917</a> <span> [<a href="https://arxiv.org/pdf/2503.14917">pdf</a>, <a href="https://arxiv.org/format/2503.14917">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiazheng Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Lu Yu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Q">Qing Cui</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhiqiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yanfang Ye</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chuxu 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="2503.14917v1-abstract-short" style="display: inline;"> High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently, numerous data selection methods have been proposed to identify subsets of data that can effectively and efficiently enhance model performance. However, most of these methods focus on general data selection and tend to o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14917v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14917v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14917v1-abstract-full" style="display: none;"> High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently, numerous data selection methods have been proposed to identify subsets of data that can effectively and efficiently enhance model performance. However, most of these methods focus on general data selection and tend to overlook the specific nuances of domain-related data. In this paper, we introduce MASS, a \textbf{MA}thematical data \textbf{S}election framework using the \textbf{S}kill graph for pretraining LLMs in the mathematical reasoning domain. By taking into account the unique characteristics of mathematics and reasoning, we construct a skill graph that captures the mathematical skills and their interrelations from a reference dataset. This skill graph guides us in assigning quality scores to the target dataset, enabling us to select the top-ranked subset which is further used to pretrain LLMs. Experimental results demonstrate the efficiency and effectiveness of MASS across different model sizes (1B and 7B) and pretraining datasets (web data and synthetic data). Specifically, in terms of efficiency, models trained on subsets selected by MASS can achieve similar performance to models trained on the original datasets, with a significant reduction in the number of trained tokens - ranging from 50\% to 70\% fewer tokens. In terms of effectiveness, when trained on the same amount of tokens, models trained on the data selected by MASS outperform those trained on the original datasets by 3.3\% to 5.9\%. These results underscore the potential of MASS to improve both the efficiency and effectiveness of pretraining LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14917v1-abstract-full').style.display = 'none'; document.getElementById('2503.14917v1-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/2503.14487">arXiv:2503.14487</a> <span> [<a href="https://arxiv.org/pdf/2503.14487">pdf</a>, <a href="https://arxiv.org/format/2503.14487">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"> DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+M">Minglei Shi</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+Z">Ziyang Yuan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haotian Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xintao Wang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+M">Mingwu Zheng</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+X">Xin Tao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wenliang Zhao</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+W">Wenzhao Zheng</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiwen Lu</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+P">Pengfei Wan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Di Zhang</a>, <a href="/search/cs?searchtype=author&query=Gai%2C+K">Kun Gai</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="2503.14487v1-abstract-short" style="display: inline;"> Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we propose a novel approach that leverages the inherent heterogeneity of the diffusion process. Our method, DiffMoE, introduces a batch-level global token pool that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14487v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14487v1-abstract-full" style="display: none;"> Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we propose a novel approach that leverages the inherent heterogeneity of the diffusion process. Our method, DiffMoE, introduces a batch-level global token pool that enables experts to access global token distributions during training, promoting specialized expert behavior. To unleash the full potential of the diffusion process, DiffMoE incorporates a capacity predictor that dynamically allocates computational resources based on noise levels and sample complexity. Through comprehensive evaluation, DiffMoE achieves state-of-the-art performance among diffusion models on ImageNet benchmark, substantially outperforming both dense architectures with 3x activated parameters and existing MoE approaches while maintaining 1x activated parameters. The effectiveness of our approach extends beyond class-conditional generation to more challenging tasks such as text-to-image generation, demonstrating its broad applicability across different diffusion model applications. Project Page: https://shiml20.github.io/DiffMoE/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14487v1-abstract-full').style.display = 'none'; document.getElementById('2503.14487v1-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://shiml20.github.io/DiffMoE/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14125">arXiv:2503.14125</a> <span> [<a href="https://arxiv.org/pdf/2503.14125">pdf</a>, <a href="https://arxiv.org/format/2503.14125">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"> Frac-Connections: Fractional Extension of Hyper-Connections </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+D">Defa Zhu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hongzhi Huang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jundong Zhou</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zihao Huang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+Y">Yutao Zeng</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+B">Banggu Wu</a>, <a href="/search/cs?searchtype=author&query=Min%2C+Q">Qiyang Min</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xun 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="2503.14125v1-abstract-short" style="display: inline;"> Residual connections are central to modern deep learning architectures, enabling the training of very deep networks by mitigating gradient vanishing. Hyper-Connections recently generalized residual connections by introducing multiple connection strengths at different depths, thereby addressing the seesaw effect between gradient vanishing and representation collapse. However, Hyper-Connections incr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14125v1-abstract-full').style.display = 'inline'; document.getElementById('2503.14125v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14125v1-abstract-full" style="display: none;"> Residual connections are central to modern deep learning architectures, enabling the training of very deep networks by mitigating gradient vanishing. Hyper-Connections recently generalized residual connections by introducing multiple connection strengths at different depths, thereby addressing the seesaw effect between gradient vanishing and representation collapse. However, Hyper-Connections increase memory access costs by expanding the width of hidden states. In this paper, we propose Frac-Connections, a novel approach that divides hidden states into multiple parts rather than expanding their width. Frac-Connections retain partial benefits of Hyper-Connections while reducing memory consumption. To validate their effectiveness, we conduct large-scale experiments on language tasks, with the largest being a 7B MoE model trained on up to 3T tokens, demonstrating that Frac-Connections significantly outperform residual connections. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14125v1-abstract-full').style.display = 'none'; document.getElementById('2503.14125v1-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/2503.13660">arXiv:2503.13660</a> <span> [<a href="https://arxiv.org/pdf/2503.13660">pdf</a>, <a href="https://arxiv.org/format/2503.13660">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="Formal Languages and Automata Theory">cs.FL</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"> INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meng%2C+Q">Qian Meng</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J+P">Jin Peng Zhou</a>, <a href="/search/cs?searchtype=author&query=Weinberger%2C+K+Q">Kilian Q. Weinberger</a>, <a href="/search/cs?searchtype=author&query=Kress-Gazit%2C+H">Hadas Kress-Gazit</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="2503.13660v1-abstract-short" style="display: inline;"> This paper presents INPROVF, an automatic framework that combines large language models (LLMs) and formal methods to speed up the repair process of high-level robot controllers. Previous approaches based solely on formal methods are computationally expensive and cannot scale to large state spaces. In contrast, INPROVF uses LLMs to generate repair candidates, and formal methods to verify their corr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13660v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13660v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13660v1-abstract-full" style="display: none;"> This paper presents INPROVF, an automatic framework that combines large language models (LLMs) and formal methods to speed up the repair process of high-level robot controllers. Previous approaches based solely on formal methods are computationally expensive and cannot scale to large state spaces. In contrast, INPROVF uses LLMs to generate repair candidates, and formal methods to verify their correctness. To improve the quality of these candidates, our framework first translates the symbolic representations of the environment and controllers into natural language descriptions. If a candidate fails the verification, INPROVF provides feedback on potential unsafe behaviors or unsatisfied tasks, and iteratively prompts LLMs to generate improved solutions. We demonstrate the effectiveness of INPROVF through 12 violations with various workspaces, tasks, and state space sizes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13660v1-abstract-full').style.display = 'none'; document.getElementById('2503.13660v1-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">To appear in ICLR 2025 Workshop: VerifAI: AI Verification in the Wild; in submission to 2025 IEEE 21th International Conference on Automation Science and Engineering (CASE), Los Angeles, CA, USA: IEEE, Aug. 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/2503.13522">arXiv:2503.13522</a> <span> [<a href="https://arxiv.org/pdf/2503.13522">pdf</a>, <a href="https://arxiv.org/ps/2503.13522">ps</a>, <a href="https://arxiv.org/format/2503.13522">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Advanced Deep Learning Methods for Protein Structure Prediction and Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+T">Tianyang Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yichao Zhang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+N">Ningyuan Deng</a>, <a href="/search/cs?searchtype=author&query=Song%2C+X">Xinyuan Song</a>, <a href="/search/cs?searchtype=author&query=Bi%2C+Z">Ziqian Bi</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+Z">Zheyu Yao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">Keyu Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Ming Li</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+Q">Qian Niu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Junyu Liu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+B">Benji Peng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Sen Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Ming Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+X">Xuanhe Pan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jinlang Wang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+P">Pohsun Feng</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Y">Yizhu Wen</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+L+K">Lawrence KQ Yan</a>, <a href="/search/cs?searchtype=author&query=Tseng%2C+H">Hongming Tseng</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+Y">Yan Zhong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yunze Wang</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+Z">Ziyuan Qin</a>, <a href="/search/cs?searchtype=author&query=Jing%2C+B">Bowen Jing</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junjie Yang</a> , et al. (3 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13522v2-abstract-short" style="display: inline;"> After AlphaFold won the Nobel Prize, protein prediction with deep learning once again became a hot topic. We comprehensively explore advanced deep learning methods applied to protein structure prediction and design. It begins by examining recent innovations in prediction architectures, with detailed discussions on improvements such as diffusion based frameworks and novel pairwise attention modules… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13522v2-abstract-full').style.display = 'inline'; document.getElementById('2503.13522v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13522v2-abstract-full" style="display: none;"> After AlphaFold won the Nobel Prize, protein prediction with deep learning once again became a hot topic. We comprehensively explore advanced deep learning methods applied to protein structure prediction and design. It begins by examining recent innovations in prediction architectures, with detailed discussions on improvements such as diffusion based frameworks and novel pairwise attention modules. The text analyses key components including structure generation, evaluation metrics, multiple sequence alignment processing, and network architecture, thereby illustrating the current state of the art in computational protein modelling. Subsequent chapters focus on practical applications, presenting case studies that range from individual protein predictions to complex biomolecular interactions. Strategies for enhancing prediction accuracy and integrating deep learning techniques with experimental validation are thoroughly explored. The later sections review the industry landscape of protein design, highlighting the transformative role of artificial intelligence in biotechnology and discussing emerging market trends and future challenges. Supplementary appendices provide essential resources such as databases and open source tools, making this volume a valuable reference for researchers and students. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13522v2-abstract-full').style.display = 'none'; document.getElementById('2503.13522v2-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">v1</span> submitted 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/2503.13269">arXiv:2503.13269</a> <span> [<a href="https://arxiv.org/pdf/2503.13269">pdf</a>, <a href="https://arxiv.org/format/2503.13269">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"> DAgent: A Relational Database-Driven Data Analysis Report Generation Agent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+W">Wenyi Xu</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Y">Yuren Mao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaolu Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chao Zhang</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+X">Xuemei Dong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengfei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yunjun Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.13269v1-abstract-short" style="display: inline;"> Relational database-driven data analysis (RDB-DA) report generation, which aims to generate data analysis reports after querying relational databases, has been widely applied in fields such as finance and healthcare. Typically, these tasks are manually completed by data scientists, making the process very labor-intensive and showing a clear need for automation. Although existing methods (e.g., Tab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13269v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13269v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13269v1-abstract-full" style="display: none;"> Relational database-driven data analysis (RDB-DA) report generation, which aims to generate data analysis reports after querying relational databases, has been widely applied in fields such as finance and healthcare. Typically, these tasks are manually completed by data scientists, making the process very labor-intensive and showing a clear need for automation. Although existing methods (e.g., Table QA or Text-to-SQL) have been proposed to reduce human dependency, they cannot handle complex analytical tasks that require multi-step reasoning, cross-table associations, and synthesizing insights into reports. Moreover, there is no dataset available for developing automatic RDB-DA report generation. To fill this gap, this paper proposes an LLM agent system for RDB-DA report generation tasks, dubbed DAgent; moreover, we construct a benchmark for automatic data analysis report generation, which includes a new dataset DA-Dataset and evaluation metrics. DAgent integrates planning, tools, and memory modules to decompose natural language questions into logically independent sub-queries, accurately retrieve key information from relational databases, and generate analytical reports that meet the requirements of completeness, correctness, and conciseness through multi-step reasoning and effective data integration. Experimental analysis on the DA-Dataset demonstrates that DAgent's superiority in retrieval performance and analysis report generation quality, showcasing its strong potential for tackling complex database analysis report generation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13269v1-abstract-full').style.display = 'none'; document.getElementById('2503.13269v1-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/2503.13109">arXiv:2503.13109</a> <span> [<a href="https://arxiv.org/pdf/2503.13109">pdf</a>, <a href="https://arxiv.org/format/2503.13109">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+K">Kedi Chen</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Z">Zhikai Lei</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+F">Fan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yinqi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qin Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Liang He</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Q">Qipeng Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">Kai Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei 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="2503.13109v1-abstract-short" style="display: inline;"> Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13109v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13109v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13109v1-abstract-full" style="display: none;"> Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning. Towards this end, we novelly employ number sequences as the source of inductive reasoning data. We package sequences into algorithmic problems to find the general term of each sequence through a code solution. In this way, we can verify whether the code solution holds for any term in the current sequence, and inject case-based supervision signals by using code unit tests. We build a sequence synthetic data pipeline and form a training dataset CodeSeq. Experimental results show that the models tuned with CodeSeq improve on both code and comprehensive reasoning benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13109v1-abstract-full').style.display = 'none'; document.getElementById('2503.13109v1-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/2503.12866">arXiv:2503.12866</a> <span> [<a href="https://arxiv.org/pdf/2503.12866">pdf</a>, <a href="https://arxiv.org/format/2503.12866">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"> SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+K">Kunlun Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zichen Liu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Y">Yuxin Peng</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiahuan 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="2503.12866v1-abstract-short" style="display: inline;"> Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as a promising approach to enhance VLM performance under such conditions. In practice, test data often arrives in batches, leading to increasing interest in the transductive TTA setting. However, existing TTA methods prima… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12866v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12866v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12866v1-abstract-full" style="display: none;"> Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as a promising approach to enhance VLM performance under such conditions. In practice, test data often arrives in batches, leading to increasing interest in the transductive TTA setting. However, existing TTA methods primarily focus on individual test samples, overlooking crucial cross-sample correlations within a batch. While recent ViT-based TTA methods have introduced batch-level adaptation, they remain suboptimal for VLMs due to inadequate integration of the text modality. To address these limitations, we propose a novel transductive TTA framework, Supportive Clique-based Attribute Prompting (SCAP), which effectively combines visual and textual information to enhance adaptation by generating fine-grained attribute prompts across test batches. SCAP first forms supportive cliques of test samples in an unsupervised manner based on visual similarity and learns an attribute prompt for each clique, capturing shared attributes critical for adaptation. For each test sample, SCAP aggregates attribute prompts from its associated cliques, providing enriched contextual information. To ensure adaptability over time, we incorporate a retention module that dynamically updates attribute prompts and their associated attributes as new data arrives. Comprehensive experiments across multiple benchmarks demonstrate that SCAP outperforms existing state-of-the-art methods, significantly advancing VLM generalization under domain shifts. Our code is available at https://github.com/zhoujiahuan1991/CVPR2025-SCAP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12866v1-abstract-full').style.display = 'none'; document.getElementById('2503.12866v1-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">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/2503.12821">arXiv:2503.12821</a> <span> [<a href="https://arxiv.org/pdf/2503.12821">pdf</a>, <a href="https://arxiv.org/format/2503.12821">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"> From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Song%2C+M">Mingyang Song</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+X">Xiaoye Qu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiawei Zhou</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yu Cheng</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="2503.12821v2-abstract-short" style="display: inline;"> Large Vision-Language Models (LVLMs) have achieved significant progress in combining visual comprehension with language generation. Despite this success, the training data of LVLMs still suffers from Long-Tail (LT) problems, where the data distribution is highly imbalanced. Previous works have mainly focused on traditional VLM architectures, i.e., CLIP or ViT, and specific tasks such as recognitio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12821v2-abstract-full').style.display = 'inline'; document.getElementById('2503.12821v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12821v2-abstract-full" style="display: none;"> Large Vision-Language Models (LVLMs) have achieved significant progress in combining visual comprehension with language generation. Despite this success, the training data of LVLMs still suffers from Long-Tail (LT) problems, where the data distribution is highly imbalanced. Previous works have mainly focused on traditional VLM architectures, i.e., CLIP or ViT, and specific tasks such as recognition and classification. Nevertheless, the exploration of LVLM (e.g. LLaVA) and more general tasks (e.g. Visual Question Answering and Visual Reasoning) remains under-explored. In this paper, we first conduct an in-depth analysis of the LT issues in LVLMs and identify two core causes: the overrepresentation of head concepts and the underrepresentation of tail concepts. Based on the above observation, we propose an $\textbf{A}$daptive $\textbf{D}$ata $\textbf{R}$efinement Framework ($\textbf{ADR}$), which consists of two stages: $\textbf{D}$ata $\textbf{R}$ebalancing ($\textbf{DR}$) and $\textbf{D}$ata $\textbf{S}$ynthesis ($\textbf{DS}$). In the DR stage, we adaptively rebalance the redundant data based on entity distributions, while in the DS stage, we leverage Denoising Diffusion Probabilistic Models (DDPMs) and scarce images to supplement underrepresented portions. Through comprehensive evaluations across eleven benchmarks, our proposed ADR effectively mitigates the long-tail problem in the training data, improving the average performance of LLaVA 1.5 relatively by 4.36%, without increasing the training data volume. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12821v2-abstract-full').style.display = 'none'; document.getElementById('2503.12821v2-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 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">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/2503.12800">arXiv:2503.12800</a> <span> [<a href="https://arxiv.org/pdf/2503.12800">pdf</a>, <a href="https://arxiv.org/format/2503.12800">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"> Pairwise Similarity Regularization for Semi-supervised Graph Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jialu Zhou</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+D">Dianxi Shi</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shaowu Yang</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+C">Chunping Qiu</a>, <a href="/search/cs?searchtype=author&query=Jing%2C+L">Luoxi Jing</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mengzhu 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="2503.12800v1-abstract-short" style="display: inline;"> With fully leveraging the value of unlabeled data, semi-supervised medical image segmentation algorithms significantly reduces the limitation of limited labeled data, achieving a significant improvement in accuracy. However, the distributional shift between labeled and unlabeled data weakens the utilization of information from the labeled data. To alleviate the problem, we propose a graph network… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12800v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12800v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12800v1-abstract-full" style="display: none;"> With fully leveraging the value of unlabeled data, semi-supervised medical image segmentation algorithms significantly reduces the limitation of limited labeled data, achieving a significant improvement in accuracy. However, the distributional shift between labeled and unlabeled data weakens the utilization of information from the labeled data. To alleviate the problem, we propose a graph network feature alignment method based on pairwise similarity regularization (PaSR) for semi-supervised medical image segmentation. PaSR aligns the graph structure of images in different domains by maintaining consistency in the pairwise structural similarity of feature graphs between the target domain and the source domain, reducing distribution shift issues in medical images. Meanwhile, further improving the accuracy of pseudo-labels in the teacher network by aligning graph clustering information to enhance the semi-supervised efficiency of the model. The experimental part was verified on three medical image segmentation benchmark datasets, with results showing improvements over advanced methods in various metrics. On the ACDC dataset, it achieved an average improvement of more than 10.66%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12800v1-abstract-full').style.display = 'none'; document.getElementById('2503.12800v1-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/2503.12541">arXiv:2503.12541</a> <span> [<a href="https://arxiv.org/pdf/2503.12541">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> </div> </div> <p class="title is-5 mathjax"> Histogram Transporter: Learning Rotation-Equivariant Orientation Histograms for High-Precision Robotic Kitting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiadong Zhou</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+Y">Yadan Zeng</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+H">Huixu Dong</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+I">I-Ming Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12541v1-abstract-short" style="display: inline;"> Robotic kitting is a critical task in industrial automation that requires the precise arrangement of objects into kits to support downstream production processes. However, when handling complex kitting tasks that involve fine-grained orientation alignment, existing approaches often suffer from limited accuracy and computational efficiency. To address these challenges, we propose Histogram Transpor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12541v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12541v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12541v1-abstract-full" style="display: none;"> Robotic kitting is a critical task in industrial automation that requires the precise arrangement of objects into kits to support downstream production processes. However, when handling complex kitting tasks that involve fine-grained orientation alignment, existing approaches often suffer from limited accuracy and computational efficiency. To address these challenges, we propose Histogram Transporter, a novel kitting framework that learns high-precision pick-and-place actions from scratch using only a few demonstrations. First, our method extracts rotation-equivariant orientation histograms (EOHs) from visual observations using an efficient Fourier-based discretization strategy. These EOHs serve a dual purpose: improving picking efficiency by directly modeling action success probabilities over high-resolution orientations and enhancing placing accuracy by serving as local, discriminative feature descriptors for object-to-placement matching. Second, we introduce a subgroup alignment strategy in the place model that compresses the full spectrum of EOHs into a compact orientation representation, enabling efficient feature matching while preserving accuracy. Finally, we examine the proposed framework on the simulated Hand-Tool Kitting Dataset (HTKD), where it outperforms competitive baselines in both success rates and computational efficiency. Further experiments on five Raven-10 tasks exhibits the remarkable adaptability of our approach, with real-robot trials confirming its applicability for real-world deployment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12541v1-abstract-full').style.display = 'none'; document.getElementById('2503.12541v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This manuscript is currently under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12205">arXiv:2503.12205</a> <span> [<a href="https://arxiv.org/pdf/2503.12205">pdf</a>, <a href="https://arxiv.org/format/2503.12205">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"> PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xiao%2C+Y">Yuan-An Xiao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weixuan Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+D">Dong Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Junwei Zhou</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+S">Shengyu Cheng</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Y">Yingfei Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12205v1-abstract-short" style="display: inline;"> Using Large Language Models (LLMs) to fix static analysis alerts in program code is becoming increasingly popular and helpful. However, these models often have the problem of hallucination and perform poorly for complex and less common alerts, limiting their performance. Retrieval-augmented generation (RAG) aims to solve this problem by providing the model with a relevant example, but the unsatisf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12205v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12205v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12205v1-abstract-full" style="display: none;"> Using Large Language Models (LLMs) to fix static analysis alerts in program code is becoming increasingly popular and helpful. However, these models often have the problem of hallucination and perform poorly for complex and less common alerts, limiting their performance. Retrieval-augmented generation (RAG) aims to solve this problem by providing the model with a relevant example, but the unsatisfactory quality of such examples challenges the effectiveness of existing approaches. To address this challenge, this paper utilizes the predicates in the analysis rule, which can serve as a bridge between the alert and relevant code snippets within a clean code corpus, called key examples. Based on the above insight, we propose an algorithm to retrieve key examples for an alert automatically. Then, we build PredicateFix as a RAG pipeline to fix alerts flagged by the CodeQL code checker and another imperative static analyzer for Golang. Evaluation with multiple LLMs shows that PredicateFix increases the number of correct repairs by 27.1% ~ 72.5%, significantly outperforming other baseline RAG approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12205v1-abstract-full').style.display = 'none'; document.getElementById('2503.12205v1-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">12 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.11855">arXiv:2503.11855</a> <span> [<a href="https://arxiv.org/pdf/2503.11855">pdf</a>, <a href="https://arxiv.org/format/2503.11855">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Learning-based Estimation of Forward Kinematics for an Orthotic Parallel Robotic Mechanism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingzong Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuhan Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaobin Zhang</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+S">Sunil Agrawal</a>, <a href="/search/cs?searchtype=author&query=Karydis%2C+K">Konstantinos Karydis</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="2503.11855v1-abstract-short" style="display: inline;"> This paper introduces a 3D parallel robot with three identical five-degree-of-freedom chains connected to a circular brace end-effector, aimed to serve as an assistive device for patients with cervical spondylosis. The inverse kinematics of the system is solved analytically, whereas learning-based methods are deployed to solve the forward kinematics. The methods considered herein include a Koopman… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11855v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11855v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11855v1-abstract-full" style="display: none;"> This paper introduces a 3D parallel robot with three identical five-degree-of-freedom chains connected to a circular brace end-effector, aimed to serve as an assistive device for patients with cervical spondylosis. The inverse kinematics of the system is solved analytically, whereas learning-based methods are deployed to solve the forward kinematics. The methods considered herein include a Koopman operator-based approach as well as a neural network-based approach. The task is to predict the position and orientation of end-effector trajectories. The dataset used to train these methods is based on the analytical solutions derived via inverse kinematics. The methods are tested both in simulation and via physical hardware experiments with the developed robot. Results validate the suitability of deploying learning-based methods for studying parallel mechanism forward kinematics that are generally hard to resolve analytically. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11855v1-abstract-full').style.display = 'none'; document.getElementById('2503.11855v1-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/2503.11346">arXiv:2503.11346</a> <span> [<a href="https://arxiv.org/pdf/2503.11346">pdf</a>, <a href="https://arxiv.org/format/2503.11346">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+F">Fengyu Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yilin Li</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Junhao Zhu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yanfei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jia Zhou</a>, <a href="/search/cs?searchtype=author&query=Zu%2C+H">Hui Zu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jingwen Zhao</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yunjun Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.11346v1-abstract-short" style="display: inline;"> Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11346v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11346v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11346v1-abstract-full" style="display: none;"> Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmented generation (RAG) and anti-hallucination multi-agents. Specifically, AIstorian introduces an in-context learning based chunking strategy and a KG-based index for accurate and efficient reference retrieval. Meanwhile, AIstorian orchestrates multi-agents to conduct on-the-fly hallucination detection and error-type-aware correction. Additionally, to teach LLMs a certain language style, we finetune LLMs based on a two-step training approach combining data augmentation-enhanced supervised fine-tuning with stylistic preference optimization. Extensive experiments on a real-life historical Jinshi dataset demonstrate that AIstorian achieves a 3.8x improvement in factual accuracy and a 47.6% reduction in hallucination rate compared to existing baselines. The data and code are available at: https://github.com/ZJU-DAILY/AIstorian. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11346v1-abstract-full').style.display = 'none'; document.getElementById('2503.11346v1-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/2503.11049">arXiv:2503.11049</a> <span> [<a href="https://arxiv.org/pdf/2503.11049">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> </div> </div> <p class="title is-5 mathjax"> Fish Mouth Inspired Origami Gripper for Robust Multi-Type Underwater Grasping </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+H">Honghao Guo</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Junda Huang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+I">Ian Zhang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+B">Boyuan Liang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xin Ma</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yunhui Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jianshu 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="2503.11049v2-abstract-short" style="display: inline;"> Robotic grasping and manipulation in underwater environments present unique challenges for robotic hands traditionally used on land. These challenges stem from dynamic water conditions, a wide range of object properties from soft to stiff, irregular object shapes, and varying surface frictions. One common approach involves developing finger-based hands with embedded compliance using underactuation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11049v2-abstract-full').style.display = 'inline'; document.getElementById('2503.11049v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11049v2-abstract-full" style="display: none;"> Robotic grasping and manipulation in underwater environments present unique challenges for robotic hands traditionally used on land. These challenges stem from dynamic water conditions, a wide range of object properties from soft to stiff, irregular object shapes, and varying surface frictions. One common approach involves developing finger-based hands with embedded compliance using underactuation and soft actuators. This study introduces an effective alternative solution that does not rely on finger-based hand designs. We present a fish mouth inspired origami gripper that utilizes a single degree of freedom to perform a variety of robust grasping tasks underwater. The innovative structure transforms a simple uniaxial pulling motion into a grasping action based on the Yoshimura crease pattern folding. The origami gripper offers distinct advantages, including scalable and optimizable design, grasping compliance, and robustness, with four grasping types: pinch, power grasp, simultaneous grasping of multiple objects, and scooping from the seabed. In this work, we detail the design, modeling, fabrication, and validation of a specialized underwater gripper capable of handling various marine creatures, including jellyfish, crabs, and abalone. By leveraging an origami and bio-inspired approach, the presented gripper demonstrates promising potential for robotic grasping and manipulation in underwater environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11049v2-abstract-full').style.display = 'none'; document.getElementById('2503.11049v2-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 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/2503.10773">arXiv:2503.10773</a> <span> [<a href="https://arxiv.org/pdf/2503.10773">pdf</a>, <a href="https://arxiv.org/format/2503.10773">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learn then Decide: A Learning Approach for Designing Data Marketplaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yingqi Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jin Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+H">Hua Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yong Chen</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+X">Xiaowu Dai</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="2503.10773v1-abstract-short" style="display: inline;"> As data marketplaces become increasingly central to the digital economy, it is crucial to design efficient pricing mechanisms that optimize revenue while ensuring fair and adaptive pricing. We introduce the Maximum Auction-to-Posted Price (MAPP) mechanism, a novel two-stage approach that first estimates the bidders' value distribution through auctions and then determines the optimal posted price b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10773v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10773v1-abstract-full" style="display: none;"> As data marketplaces become increasingly central to the digital economy, it is crucial to design efficient pricing mechanisms that optimize revenue while ensuring fair and adaptive pricing. We introduce the Maximum Auction-to-Posted Price (MAPP) mechanism, a novel two-stage approach that first estimates the bidders' value distribution through auctions and then determines the optimal posted price based on the learned distribution. We establish that MAPP is individually rational and incentive-compatible, ensuring truthful bidding while balancing revenue maximization with minimal price discrimination. MAPP achieves a regret of $O_p(n^{-1})$ when incorporating historical bid data, where $n$ is the number of bids in the current round. It outperforms existing methods while imposing weaker distributional assumptions. For sequential dataset sales over $T$ rounds, we propose an online MAPP mechanism that dynamically adjusts pricing across datasets with varying value distributions. Our approach achieves no-regret learning, with the average cumulative regret converging at a rate of $O_p(T^{-1/2}(\log T)^2)$. We validate the effectiveness of MAPP through simulations and real-world data from the FCC AWS-3 spectrum auction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10773v1-abstract-full').style.display = 'none'; document.getElementById('2503.10773v1-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/2503.10630">arXiv:2503.10630</a> <span> [<a href="https://arxiv.org/pdf/2503.10630">pdf</a>, <a href="https://arxiv.org/format/2503.10630">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"> UniGoal: Towards Universal Zero-shot Goal-oriented Navigation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hang Yin</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiuwei Xu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+L">Lingqing Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Ziwei Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jie Zhou</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiwen Lu</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="2503.10630v3-abstract-short" style="display: inline;"> In this paper, we propose a general framework for universal zero-shot goal-oriented navigation. Existing zero-shot methods build inference framework upon large language models (LLM) for specific tasks, which differs a lot in overall pipeline and fails to generalize across different types of goal. Towards the aim of universal zero-shot navigation, we propose a uniform graph representation to unify… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10630v3-abstract-full').style.display = 'inline'; document.getElementById('2503.10630v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10630v3-abstract-full" style="display: none;"> In this paper, we propose a general framework for universal zero-shot goal-oriented navigation. Existing zero-shot methods build inference framework upon large language models (LLM) for specific tasks, which differs a lot in overall pipeline and fails to generalize across different types of goal. Towards the aim of universal zero-shot navigation, we propose a uniform graph representation to unify different goals, including object category, instance image and text description. We also convert the observation of agent into an online maintained scene graph. With this consistent scene and goal representation, we preserve most structural information compared with pure text and are able to leverage LLM for explicit graph-based reasoning. Specifically, we conduct graph matching between the scene graph and goal graph at each time instant and propose different strategies to generate long-term goal of exploration according to different matching states. The agent first iteratively searches subgraph of goal when zero-matched. With partial matching, the agent then utilizes coordinate projection and anchor pair alignment to infer the goal location. Finally scene graph correction and goal verification are applied for perfect matching. We also present a blacklist mechanism to enable robust switch between stages. Extensive experiments on several benchmarks show that our UniGoal achieves state-of-the-art zero-shot performance on three studied navigation tasks with a single model, even outperforming task-specific zero-shot methods and supervised universal methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10630v3-abstract-full').style.display = 'none'; document.getElementById('2503.10630v3-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 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 to CVPR 2025. Project page: https://bagh2178.github.io/UniGoal/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.10437">arXiv:2503.10437</a> <span> [<a href="https://arxiv.org/pdf/2503.10437">pdf</a>, <a href="https://arxiv.org/format/2503.10437">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"> 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wanhua Li</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+R">Renping Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jiawei Zhou</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Y">Yingwei Song</a>, <a href="/search/cs?searchtype=author&query=Herter%2C+J">Johannes Herter</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+M">Minghan Qin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Gao Huang</a>, <a href="/search/cs?searchtype=author&query=Pfister%2C+H">Hanspeter Pfister</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="2503.10437v1-abstract-short" style="display: inline;"> Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations, achieving precision and efficiency in 3D static scenes, it lacks the ability to handle dynamic 4D fields as CLIP, designed for static image-text tasks, cannot capture t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10437v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10437v1-abstract-full" style="display: none;"> Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations, achieving precision and efficiency in 3D static scenes, it lacks the ability to handle dynamic 4D fields as CLIP, designed for static image-text tasks, cannot capture temporal dynamics in videos. Real-world environments are inherently dynamic, with object semantics evolving over time. Building a precise 4D language field necessitates obtaining pixel-aligned, object-wise video features, which current vision models struggle to achieve. To address these challenges, we propose 4D LangSplat, which learns 4D language fields to handle time-agnostic or time-sensitive open-vocabulary queries in dynamic scenes efficiently. 4D LangSplat bypasses learning the language field from vision features and instead learns directly from text generated from object-wise video captions via Multimodal Large Language Models (MLLMs). Specifically, we propose a multimodal object-wise video prompting method, consisting of visual and text prompts that guide MLLMs to generate detailed, temporally consistent, high-quality captions for objects throughout a video. These captions are encoded using a Large Language Model into high-quality sentence embeddings, which then serve as pixel-aligned, object-specific feature supervision, facilitating open-vocabulary text queries through shared embedding spaces. Recognizing that objects in 4D scenes exhibit smooth transitions across states, we further propose a status deformable network to model these continuous changes over time effectively. Our results across multiple benchmarks demonstrate that 4D LangSplat attains precise and efficient results for both time-sensitive and time-agnostic open-vocabulary queries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10437v1-abstract-full').style.display = 'none'; document.getElementById('2503.10437v1-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">CVPR 2025. Project Page: https://4d-langsplat.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/2503.10166">arXiv:2503.10166</a> <span> [<a href="https://arxiv.org/pdf/2503.10166">pdf</a>, <a href="https://arxiv.org/format/2503.10166">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+P">Pengfei Luo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingbo Zhou</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tong Xu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yuan Xia</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Linli Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+E">Enhong Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.10166v1-abstract-short" style="display: inline;"> With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large multimodal models (LMMs) has significantly facilitated these tasks, existing approaches often address them in isolation, requiring the construction of separate s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10166v1-abstract-full').style.display = 'inline'; document.getElementById('2503.10166v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.10166v1-abstract-full" style="display: none;"> With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large multimodal models (LMMs) has significantly facilitated these tasks, existing approaches often address them in isolation, requiring the construction of separate systems for each task. This not only increases system complexity and maintenance costs, but also exacerbates challenges stemming from language ambiguity and complex image content, making it difficult for retrieval systems to provide accurate and reliable results. To this end, we propose ImageScope, a training-free, three-stage framework that leverages collective reasoning to unify LGIR tasks. The key insight behind the unification lies in the compositional nature of language, which transforms diverse LGIR tasks into a generalized text-to-image retrieval process, along with the reasoning of LMMs serving as a universal verification to refine the results. To be specific, in the first stage, we improve the robustness of the framework by synthesizing search intents across varying levels of semantic granularity using chain-of-thought (CoT) reasoning. In the second and third stages, we then reflect on retrieval results by verifying predicate propositions locally, and performing pairwise evaluations globally. Experiments conducted on six LGIR datasets demonstrate that ImageScope outperforms competitive baselines. Comprehensive evaluations and ablation studies further confirm the effectiveness of our design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.10166v1-abstract-full').style.display = 'none'; document.getElementById('2503.10166v1-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">WWW 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/2503.09959">arXiv:2503.09959</a> <span> [<a href="https://arxiv.org/pdf/2503.09959">pdf</a>, <a href="https://arxiv.org/format/2503.09959">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"> RMG: Real-Time Expressive Motion Generation with Self-collision Avoidance for 6-DOF Companion Robotic Arms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiansheng Li</a>, <a href="/search/cs?searchtype=author&query=Song%2C+H">Haotian Song</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jinni Zhou</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+Q">Qiang Nie</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Y">Yi 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="2503.09959v1-abstract-short" style="display: inline;"> The six-degree-of-freedom (6-DOF) robotic arm has gained widespread application in human-coexisting environments. While previous research has predominantly focused on functional motion generation, the critical aspect of expressive motion in human-robot interaction remains largely unexplored. This paper presents a novel real-time motion generation planner that enhances interactivity by creating exp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09959v1-abstract-full').style.display = 'inline'; document.getElementById('2503.09959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.09959v1-abstract-full" style="display: none;"> The six-degree-of-freedom (6-DOF) robotic arm has gained widespread application in human-coexisting environments. While previous research has predominantly focused on functional motion generation, the critical aspect of expressive motion in human-robot interaction remains largely unexplored. This paper presents a novel real-time motion generation planner that enhances interactivity by creating expressive robotic motions between arbitrary start and end states within predefined time constraints. Our approach involves three key contributions: first, we develop a mapping algorithm to construct an expressive motion dataset derived from human dance movements; second, we train motion generation models in both Cartesian and joint spaces using this dataset; third, we introduce an optimization algorithm that guarantees smooth, collision-free motion while maintaining the intended expressive style. Experimental results demonstrate the effectiveness of our method, which can generate expressive and generalized motions in under 0.5 seconds while satisfying all specified constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.09959v1-abstract-full').style.display = 'none'; document.getElementById('2503.09959v1-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=Zhou%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhou%2C+J&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