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 8,083 results for author: <span class="mathjax">Chen, Z</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/" aria-role="search"> <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="Chen, Z"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Chen%2C+Z&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Chen, Z"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.14837">arXiv:2502.14837</a> <span> [<a href="https://arxiv.org/pdf/2502.14837">pdf</a>, <a href="https://arxiv.org/format/2502.14837">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"> Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ji%2C+T">Tao Ji</a>, <a href="/search/?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/?searchtype=author&query=Wu%2C+Y">Yuanbin Wu</a>, <a href="/search/?searchtype=author&query=Guo%2C+Q">Qipeng Guo</a>, <a href="/search/?searchtype=author&query=Shen%2C+L">Lixing Shen</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan Chen</a>, <a href="/search/?searchtype=author&query=Qiu%2C+X">Xipeng Qiu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a>, <a href="/search/?searchtype=author&query=Gui%2C+T">Tao Gui</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="2502.14837v1-abstract-short" style="display: inline;"> Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA, standard LLMs employing Multi-Head Attention (MHA) and its variants such as Grouped-Query Attention (GQA) exhibit significant cost disadvantages. Enabling well-trained… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14837v1-abstract-full').style.display = 'inline'; document.getElementById('2502.14837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.14837v1-abstract-full" style="display: none;"> Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA, standard LLMs employing Multi-Head Attention (MHA) and its variants such as Grouped-Query Attention (GQA) exhibit significant cost disadvantages. Enabling well-trained LLMs (e.g., Llama) to rapidly adapt to MLA without pre-training from scratch is both meaningful and challenging. This paper proposes the first data-efficient fine-tuning method for transitioning from MHA to MLA (MHA2MLA), which includes two key components: for partial-RoPE, we remove RoPE from dimensions of queries and keys that contribute less to the attention scores, for low-rank approximation, we introduce joint SVD approximations based on the pre-trained parameters of keys and values. These carefully designed strategies enable MHA2MLA to recover performance using only a small fraction (0.3% to 0.6%) of the data, significantly reducing inference costs while seamlessly integrating with compression techniques such as KV cache quantization. For example, the KV cache size of Llama2-7B is reduced by 92.19%, with only a 0.5% drop in LongBench performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14837v1-abstract-full').style.display = 'none'; document.getElementById('2502.14837v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">16 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.14247">arXiv:2502.14247</a> <span> [<a href="https://arxiv.org/pdf/2502.14247">pdf</a>, <a href="https://arxiv.org/format/2502.14247">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yang%2C+J">Jiayu Yang</a>, <a href="/search/?searchtype=author&query=Shang%2C+T">Taizhang Shang</a>, <a href="/search/?searchtype=author&query=Sun%2C+W">Weixuan Sun</a>, <a href="/search/?searchtype=author&query=Song%2C+X">Xibin Song</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Ziang Chen</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Senbo Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+S">Shenzhou Chen</a>, <a href="/search/?searchtype=author&query=Liu%2C+W">Weizhe Liu</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Hongdong Li</a>, <a href="/search/?searchtype=author&query=Ji%2C+P">Pan Ji</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="2502.14247v1-abstract-short" style="display: inline;"> This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text descriptions. The framework consists of 3D shape generation and texture generation. (1). The 3D shape generation pipeline employs a Variational Autoencoder (VAE) to encode implicit 3D geometries into a latent space and a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14247v1-abstract-full').style.display = 'inline'; document.getElementById('2502.14247v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.14247v1-abstract-full" style="display: none;"> This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text descriptions. The framework consists of 3D shape generation and texture generation. (1). The 3D shape generation pipeline employs a Variational Autoencoder (VAE) to encode implicit 3D geometries into a latent space and a diffusion network to generate latents conditioned on input prompts, with modifications to enhance model capacity. An alternative Artist-Created Mesh (AM) generation approach is also explored, yielding promising results for simpler geometries. (2). Texture generation involves a multi-stage process starting with frontal images generation followed by multi-view images generation, RGB-to-PBR texture conversion, and high-resolution multi-view texture refinement. A consistency scheduler is plugged into every stage, to enforce pixel-wise consistency among multi-view textures during inference, ensuring seamless integration. The pipeline demonstrates effective handling of diverse input formats, leveraging advanced neural architectures and novel methodologies to produce high-quality 3D content. This report details the system architecture, experimental results, and potential future directions to improve and expand the framework. The source code and pretrained weights are released at: \url{https://github.com/Tencent/Tencent-XR-3DGen}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14247v1-abstract-full').style.display = 'none'; document.getElementById('2502.14247v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">Tencent XR 3D Gen</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.14208">arXiv:2502.14208</a> <span> [<a href="https://arxiv.org/pdf/2502.14208">pdf</a>, <a href="https://arxiv.org/ps/2502.14208">ps</a>, <a href="https://arxiv.org/format/2502.14208">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="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> A Non-Asymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zaiwei Chen</a>, <a href="/search/?searchtype=author&query=Zhang%2C+S">Sheng Zhang</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zhe Zhang</a>, <a href="/search/?searchtype=author&query=Haque%2C+S+U">Shaan Ul Haque</a>, <a href="/search/?searchtype=author&query=Maguluri%2C+S+T">Siva Theja Maguluri</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="2502.14208v1-abstract-short" style="display: inline;"> We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the non-asymptotic behavior of iterative algorithms in both deterministic and stochastic settings. Specifically, in the deterministic setting, we prove a fixed-point theorem for seminorm-contractive operators, showing that iterates converge geometrically to the kernel of t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14208v1-abstract-full').style.display = 'inline'; document.getElementById('2502.14208v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.14208v1-abstract-full" style="display: none;"> We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the non-asymptotic behavior of iterative algorithms in both deterministic and stochastic settings. Specifically, in the deterministic setting, we prove a fixed-point theorem for seminorm-contractive operators, showing that iterates converge geometrically to the kernel of the seminorm. In the stochastic setting, we analyze the corresponding stochastic approximation (SA) algorithm under seminorm-contractive operators and Markovian noise, providing a finite-sample analysis for various stepsize choices. A benchmark for equation solving is linear systems of equations, where the convergence behavior of fixed-point iteration is closely tied to the stability of linear dynamical systems. In this special case, our results provide a complete characterization of system stability with respect to a seminorm, linking it to the solution of a Lyapunov equation in terms of positive semi-definite matrices. In the stochastic setting, we establish a finite-sample analysis for linear Markovian SA without requiring the Hurwitzness assumption. Our theoretical results offer a unified framework for deriving finite-sample bounds for various reinforcement learning algorithms in the average reward setting, including TD($位$) for policy evaluation (which is a special case of solving a Poisson equation) and Q-learning for control. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14208v1-abstract-full').style.display = 'none'; document.getElementById('2502.14208v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13990">arXiv:2502.13990</a> <span> [<a href="https://arxiv.org/pdf/2502.13990">pdf</a>, <a href="https://arxiv.org/format/2502.13990">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Remote Sensing Semantic Segmentation Quality Assessment based on Vision Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Shi%2C+H">Huiying Shi</a>, <a href="/search/?searchtype=author&query=Tan%2C+Z">Zhihong Tan</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zhihan Zhang</a>, <a href="/search/?searchtype=author&query=Wei%2C+H">Hongchen Wei</a>, <a href="/search/?searchtype=author&query=Hu%2C+Y">Yaosi Hu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yingxue Zhang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhenzhong 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="2502.13990v1-abstract-short" style="display: inline;"> The complexity of scenes and variations in image quality result in significant variability in the performance of semantic segmentation methods of remote sensing imagery (RSI) in supervised real-world scenarios. This makes the evaluation of semantic segmentation quality in such scenarios an issue to be resolved. However, most of the existing evaluation metrics are developed based on expert-labeled… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13990v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13990v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13990v1-abstract-full" style="display: none;"> The complexity of scenes and variations in image quality result in significant variability in the performance of semantic segmentation methods of remote sensing imagery (RSI) in supervised real-world scenarios. This makes the evaluation of semantic segmentation quality in such scenarios an issue to be resolved. However, most of the existing evaluation metrics are developed based on expert-labeled object-level annotations, which are not applicable in such scenarios. To address this issue, we propose RS-SQA, an unsupervised quality assessment model for RSI semantic segmentation based on vision language model (VLM). This framework leverages a pre-trained RS VLM for semantic understanding and utilizes intermediate features from segmentation methods to extract implicit information about segmentation quality. Specifically, we introduce CLIP-RS, a large-scale pre-trained VLM trained with purified text to reduce textual noise and capture robust semantic information in the RS domain. Feature visualizations confirm that CLIP-RS can effectively differentiate between various levels of segmentation quality. Semantic features and low-level segmentation features are effectively integrated through a semantic-guided approach to enhance evaluation accuracy. To further support the development of RS semantic segmentation quality assessment, we present RS-SQED, a dedicated dataset sampled from four major RS semantic segmentation datasets and annotated with segmentation accuracy derived from the inference results of 8 representative segmentation methods. Experimental results on the established dataset demonstrate that RS-SQA significantly outperforms state-of-the-art quality assessment models. This provides essential support for predicting segmentation accuracy and high-quality semantic segmentation interpretation, offering substantial practical value. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13990v1-abstract-full').style.display = 'none'; document.getElementById('2502.13990v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">16 pages,6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13965">arXiv:2502.13965</a> <span> [<a href="https://arxiv.org/pdf/2502.13965">pdf</a>, <a href="https://arxiv.org/format/2502.13965">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Autellix: An Efficient Serving Engine for LLM Agents as General Programs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Luo%2C+M">Michael Luo</a>, <a href="/search/?searchtype=author&query=Shi%2C+X">Xiaoxiang Shi</a>, <a href="/search/?searchtype=author&query=Cai%2C+C">Colin Cai</a>, <a href="/search/?searchtype=author&query=Zhang%2C+T">Tianjun Zhang</a>, <a href="/search/?searchtype=author&query=Wong%2C+J">Justin Wong</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yichuan Wang</a>, <a href="/search/?searchtype=author&query=Wang%2C+C">Chi Wang</a>, <a href="/search/?searchtype=author&query=Huang%2C+Y">Yanping Huang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhifeng Chen</a>, <a href="/search/?searchtype=author&query=Gonzalez%2C+J+E">Joseph E. Gonzalez</a>, <a href="/search/?searchtype=author&query=Stoica%2C+I">Ion Stoica</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="2502.13965v1-abstract-short" style="display: inline;"> Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs sub… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13965v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13965v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13965v1-abstract-full" style="display: none;"> Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs submitted to LLM serving engines experience long cumulative wait times, primarily due to head-of-line blocking at both the individual LLM request and the program. To address this, we introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies. Autellix intercepts LLM calls submitted by programs, enriching schedulers with program-level context. We propose two scheduling algorithms-for single-threaded and distributed programs-that preempt and prioritize LLM calls based on their programs' previously completed calls. Our evaluation demonstrates that across diverse LLMs and agentic workloads, Autellix improves throughput of programs by 4-15x at the same latency compared to state-of-the-art systems, such as vLLM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13965v1-abstract-full').style.display = 'none'; document.getElementById('2502.13965v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13943">arXiv:2502.13943</a> <span> [<a href="https://arxiv.org/pdf/2502.13943">pdf</a>, <a href="https://arxiv.org/format/2502.13943">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <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"> AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+Y">Yuliang Liu</a>, <a href="/search/?searchtype=author&query=Lu%2C+J">Junjie Lu</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhaoling Chen</a>, <a href="/search/?searchtype=author&query=Qu%2C+C">Chaofeng Qu</a>, <a href="/search/?searchtype=author&query=Liu%2C+J+K">Jason Klein Liu</a>, <a href="/search/?searchtype=author&query=Liu%2C+C">Chonghan Liu</a>, <a href="/search/?searchtype=author&query=Cai%2C+Z">Zefan Cai</a>, <a href="/search/?searchtype=author&query=Xia%2C+Y">Yunhui Xia</a>, <a href="/search/?searchtype=author&query=Zhao%2C+L">Li Zhao</a>, <a href="/search/?searchtype=author&query=Bian%2C+J">Jiang Bian</a>, <a href="/search/?searchtype=author&query=Zhang%2C+C">Chuheng Zhang</a>, <a href="/search/?searchtype=author&query=Shen%2C+W">Wei Shen</a>, <a href="/search/?searchtype=author&query=Lin%2C+Z">Zhouhan Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.13943v1-abstract-short" style="display: inline;"> Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose Ada… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13943v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13943v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13943v1-abstract-full" style="display: none;"> Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the next word. This division method provides more decision-making information at each step, enhancing downstream tasks, such as reward model learning. Moreover, our method does not require manual annotation. We demonstrate its effectiveness through experiments with AdaptiveStep-trained PRMs in mathematical reasoning and code generation tasks. Experimental results indicate that the outcome PRM achieves state-of-the-art Best-of-N performance, surpassing greedy search strategy with token-level value-guided decoding, while also reducing construction costs by over 30% compared to existing open-source PRMs. In addition, we provide a thorough analysis and case study on the PRM's performance, transferability, and generalization capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13943v1-abstract-full').style.display = 'none'; document.getElementById('2502.13943v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">17 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/2502.13794">arXiv:2502.13794</a> <span> [<a href="https://arxiv.org/pdf/2502.13794">pdf</a>, <a href="https://arxiv.org/format/2502.13794">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"> LESA: Learnable LLM Layer Scaling-Up </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yang%2C+Y">Yifei Yang</a>, <a href="/search/?searchtype=author&query=Cao%2C+Z">Zouying Cao</a>, <a href="/search/?searchtype=author&query=Ma%2C+X">Xinbei Ma</a>, <a href="/search/?searchtype=author&query=Yao%2C+Y">Yao Yao</a>, <a href="/search/?searchtype=author&query=Qin%2C+L">Libo Qin</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhi Chen</a>, <a href="/search/?searchtype=author&query=Zhao%2C+H">Hai Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.13794v1-abstract-short" style="display: inline;"> Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower converge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13794v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13794v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13794v1-abstract-full" style="display: none;"> Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower convergence during continual pre-training. We propose \textbf{LESA}, a novel learnable method for depth scaling-up. By concatenating parameters from each layer and applying Singular Value Decomposition, we uncover latent patterns between layers, suggesting that inter-layer parameters can be learned. LESA uses a neural network to predict the parameters inserted between adjacent layers, enabling better initialization and faster training. Experiments show that LESA outperforms existing baselines, achieving superior performance with less than half the computational cost during continual pre-training. Extensive analyses demonstrate its effectiveness across different model sizes and tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13794v1-abstract-full').style.display = 'none'; document.getElementById('2502.13794v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13607">arXiv:2502.13607</a> <span> [<a href="https://arxiv.org/pdf/2502.13607">pdf</a>, <a href="https://arxiv.org/format/2502.13607">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Environmental Influences on Collaboration Network Evolution: A Historical Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Williams%2C+P+R">Peter R Williams</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan 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="2502.13607v1-abstract-short" style="display: inline;"> We analysed two large collaboration networks -- the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020) -- to quantify network responses to major historical events. Our analysis revealed four properties of network-environment interaction. First, historical events can influence network evolution, with effects persisting far longer than previously recognised; the academic ne… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13607v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13607v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13607v1-abstract-full" style="display: none;"> We analysed two large collaboration networks -- the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020) -- to quantify network responses to major historical events. Our analysis revealed four properties of network-environment interaction. First, historical events can influence network evolution, with effects persisting far longer than previously recognised; the academic network showed 45\% declines during World Wars and 90\% growth during La Belle Epoque. Second, node and edge processes exhibited different environmental sensitivities; while node addition/removal tracked historical events, edge formation maintained stable statistical properties even during major disruptions. Third, different collaboration networks showed distinct response patterns; academic networks displayed sharp disruptions and rapid recoveries, while entertainment networks showed gradual changes and greater resilience. Fourth, both networks developed increasing resilience. Our results provide new insights for modelling network evolution and managing collaborative systems during periods of external disruption. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13607v1-abstract-full').style.display = 'none'; document.getElementById('2502.13607v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13540">arXiv:2502.13540</a> <span> [<a href="https://arxiv.org/pdf/2502.13540">pdf</a>, <a href="https://arxiv.org/format/2502.13540">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Amplitude analysis of $蠄(3686)\to 纬K_S^0 K_S^0 $ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=BESIII+Collaboration"> BESIII Collaboration</a>, <a href="/search/?searchtype=author&query=Ablikim%2C+M">M. Ablikim</a>, <a href="/search/?searchtype=author&query=Achasov%2C+M+N">M. N. Achasov</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Ai%2C+X+C">X. C. Ai</a>, <a href="/search/?searchtype=author&query=Aliberti%2C+R">R. Aliberti</a>, <a href="/search/?searchtype=author&query=Amoroso%2C+A">A. Amoroso</a>, <a href="/search/?searchtype=author&query=An%2C+Q">Q. An</a>, <a href="/search/?searchtype=author&query=Bai%2C+Y">Y. Bai</a>, <a href="/search/?searchtype=author&query=Bakina%2C+O">O. Bakina</a>, <a href="/search/?searchtype=author&query=Ban%2C+Y">Y. Ban</a>, <a href="/search/?searchtype=author&query=Bao%2C+H+-">H. -R. Bao</a>, <a href="/search/?searchtype=author&query=Batozskaya%2C+V">V. Batozskaya</a>, <a href="/search/?searchtype=author&query=Begzsuren%2C+K">K. Begzsuren</a>, <a href="/search/?searchtype=author&query=Berger%2C+N">N. Berger</a>, <a href="/search/?searchtype=author&query=Berlowski%2C+M">M. Berlowski</a>, <a href="/search/?searchtype=author&query=Bertani%2C+M">M. Bertani</a>, <a href="/search/?searchtype=author&query=Bettoni%2C+D">D. Bettoni</a>, <a href="/search/?searchtype=author&query=Bianchi%2C+F">F. Bianchi</a>, <a href="/search/?searchtype=author&query=Bianco%2C+E">E. Bianco</a>, <a href="/search/?searchtype=author&query=Bortone%2C+A">A. Bortone</a>, <a href="/search/?searchtype=author&query=Boyko%2C+I">I. Boyko</a>, <a href="/search/?searchtype=author&query=Briere%2C+R+A">R. A. Briere</a>, <a href="/search/?searchtype=author&query=Brueggemann%2C+A">A. Brueggemann</a>, <a href="/search/?searchtype=author&query=Cai%2C+H">H. Cai</a> , et al. (704 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="2502.13540v1-abstract-short" style="display: inline;"> Using $(2712\pm14)\times10^6$ $蠄(3686)$ events collected with the BESIII detector, we perform the first amplitude analysis of the radiative decay $蠄(3686)\to 纬K_S^0 K_S^0$ within the mass region $M_{K_S^0 K_S^0 }<2.8$ GeV/$c^2$. Employing a one-channel K-matrix approach for the description of the dynamics of the $K^0_S K^0_S$ system, the data sample is well described with four poles for the $f_0$-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13540v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13540v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13540v1-abstract-full" style="display: none;"> Using $(2712\pm14)\times10^6$ $蠄(3686)$ events collected with the BESIII detector, we perform the first amplitude analysis of the radiative decay $蠄(3686)\to 纬K_S^0 K_S^0$ within the mass region $M_{K_S^0 K_S^0 }<2.8$ GeV/$c^2$. Employing a one-channel K-matrix approach for the description of the dynamics of the $K^0_S K^0_S$ system, the data sample is well described with four poles for the $f_0$-wave and three poles for the $f_2$-wave. The determined pole positions are consistent with those of well-established resonance states. The observed $f_0$ and $f_{2}$ states are found to be qualitatively consistent with those produced in radiative $J/蠄$ decays, indicating the similarity between the two charmonium states in their radiative decays. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13540v1-abstract-full').style.display = 'none'; document.getElementById('2502.13540v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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, 4 figures, submitted to JHEP</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13499">arXiv:2502.13499</a> <span> [<a href="https://arxiv.org/pdf/2502.13499">pdf</a>, <a href="https://arxiv.org/format/2502.13499">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <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"> Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Ziwei Chen</a>, <a href="/search/?searchtype=author&query=Shen%2C+J">Jiawen Shen</a>, <a href="/search/?searchtype=author&query=Luna"> Luna</a>, <a href="/search/?searchtype=author&query=Vaccaro%2C+K">Kristen Vaccaro</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="2502.13499v1-abstract-short" style="display: inline;"> Recent work has highlighted the risks of LLM-generated content for a wide range of harmful behaviors, including incorrect and harmful code. In this work, we extend this by studying whether LLM-generated web design contains dark patterns. This work evaluated designs of ecommerce web components generated by four popular LLMs: Claude, GPT, Gemini, and Llama. We tested 13 commonly used ecommerce compo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13499v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13499v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13499v1-abstract-full" style="display: none;"> Recent work has highlighted the risks of LLM-generated content for a wide range of harmful behaviors, including incorrect and harmful code. In this work, we extend this by studying whether LLM-generated web design contains dark patterns. This work evaluated designs of ecommerce web components generated by four popular LLMs: Claude, GPT, Gemini, and Llama. We tested 13 commonly used ecommerce components (e.g., search, product reviews) and used them as prompts to generate a total of 312 components across all models. Over one-third of generated components contain at least one dark pattern. The majority of dark pattern strategies involve hiding crucial information, limiting users' actions, and manipulating them into making decisions through a sense of urgency. Dark patterns are also more frequently produced in components that are related to company interests. These findings highlight the need for interventions to prevent dark patterns during front-end code generation with LLMs and emphasize the importance of expanding ethical design education to a broader audience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13499v1-abstract-full').style.display = 'none'; document.getElementById('2502.13499v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13299">arXiv:2502.13299</a> <span> [<a href="https://arxiv.org/pdf/2502.13299">pdf</a>, <a href="https://arxiv.org/format/2502.13299">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Measurement of the inelasticity distribution of neutrino-nucleon interactions for $\mathbf{80~GeV<E_谓<560~GeV}$ with IceCube DeepCore </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=IceCube+Collaboration"> IceCube Collaboration</a>, <a href="/search/?searchtype=author&query=Abbasi%2C+R">R. Abbasi</a>, <a href="/search/?searchtype=author&query=Ackermann%2C+M">M. Ackermann</a>, <a href="/search/?searchtype=author&query=Adams%2C+J">J. Adams</a>, <a href="/search/?searchtype=author&query=Agarwalla%2C+S+K">S. K. Agarwalla</a>, <a href="/search/?searchtype=author&query=Aguilar%2C+J+A">J. A. Aguilar</a>, <a href="/search/?searchtype=author&query=Ahlers%2C+M">M. Ahlers</a>, <a href="/search/?searchtype=author&query=Alameddine%2C+J+M">J. M. Alameddine</a>, <a href="/search/?searchtype=author&query=Amin%2C+N+M">N. M. Amin</a>, <a href="/search/?searchtype=author&query=Andeen%2C+K">K. Andeen</a>, <a href="/search/?searchtype=author&query=Arg%C3%BCelles%2C+C">C. Arg眉elles</a>, <a href="/search/?searchtype=author&query=Ashida%2C+Y">Y. Ashida</a>, <a href="/search/?searchtype=author&query=Athanasiadou%2C+S">S. Athanasiadou</a>, <a href="/search/?searchtype=author&query=Axani%2C+S+N">S. N. Axani</a>, <a href="/search/?searchtype=author&query=Babu%2C+R">R. Babu</a>, <a href="/search/?searchtype=author&query=Bai%2C+X">X. Bai</a>, <a href="/search/?searchtype=author&query=V.%2C+A+B">A. Balagopal V.</a>, <a href="/search/?searchtype=author&query=Baricevic%2C+M">M. Baricevic</a>, <a href="/search/?searchtype=author&query=Barwick%2C+S+W">S. W. Barwick</a>, <a href="/search/?searchtype=author&query=Bash%2C+S">S. Bash</a>, <a href="/search/?searchtype=author&query=Basu%2C+V">V. Basu</a>, <a href="/search/?searchtype=author&query=Bay%2C+R">R. Bay</a>, <a href="/search/?searchtype=author&query=Beatty%2C+J+J">J. J. Beatty</a>, <a href="/search/?searchtype=author&query=Tjus%2C+J+B">J. Becker Tjus</a>, <a href="/search/?searchtype=author&query=Beise%2C+J">J. Beise</a> , et al. (404 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="2502.13299v1-abstract-short" style="display: inline;"> We report a measurement of the inelasticity distribution in the scattering of neutrinos of energy $80-560$ GeV off nucleons, which is sensitive to the inclusive differential cross section. This analysis is based on a sample of atmospheric muon neutrinos detected in the IceCube sub-array DeepCore during 2012-2021, and is the first such measurement in this energy range. Our measurement extends to en… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13299v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13299v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13299v1-abstract-full" style="display: none;"> We report a measurement of the inelasticity distribution in the scattering of neutrinos of energy $80-560$ GeV off nucleons, which is sensitive to the inclusive differential cross section. This analysis is based on a sample of atmospheric muon neutrinos detected in the IceCube sub-array DeepCore during 2012-2021, and is the first such measurement in this energy range. Our measurement extends to energies where accelerator data is not available, hence we compare our results to predictions from perturbative QCD calculations, finding good agreement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13299v1-abstract-full').style.display = 'none'; document.getElementById('2502.13299v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">17 pages, 19 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/2502.12879">arXiv:2502.12879</a> <span> [<a href="https://arxiv.org/pdf/2502.12879">pdf</a>, <a href="https://arxiv.org/ps/2502.12879">ps</a>, <a href="https://arxiv.org/format/2502.12879">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Two-way affine automata can verify every language </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zeyu Chen</a>, <a href="/search/?searchtype=author&query=Yakary%C4%B1lmaz%2C+A">Abuzer Yakary谋lmaz</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="2502.12879v1-abstract-short" style="display: inline;"> When used as verifiers in Arthur-Merlin systems, two-way quantum finite automata can verify membership in all languages with bounded error with double-exponential expected running time, which cannot be achieved by their classical counterparts. We obtain the same result for affine automata with single-exponential expected time. We show that every binary (and r-ary) language is verified by some two-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12879v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12879v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12879v1-abstract-full" style="display: none;"> When used as verifiers in Arthur-Merlin systems, two-way quantum finite automata can verify membership in all languages with bounded error with double-exponential expected running time, which cannot be achieved by their classical counterparts. We obtain the same result for affine automata with single-exponential expected time. We show that every binary (and r-ary) language is verified by some two-way affine finite automata verifiers by presenting two protocols: A weak verification protocol uses a single affine register and the input is read once; and, a strong verification protocol uses two affine registers. These results reflects the remarkable verification capabilities of affine finite automata. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12879v1-abstract-full').style.display = 'none'; document.getElementById('2502.12879v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12724">arXiv:2502.12724</a> <span> [<a href="https://arxiv.org/pdf/2502.12724">pdf</a>, <a href="https://arxiv.org/format/2502.12724">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"> Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhuoqun Chen</a>, <a href="/search/?searchtype=author&query=Yuan%2C+X">Xiu Yuan</a>, <a href="/search/?searchtype=author&query=Mu%2C+T">Tongzhou Mu</a>, <a href="/search/?searchtype=author&query=Su%2C+H">Hao Su</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.12724v1-abstract-short" style="display: inline;"> Imitation learning is an efficient method for teaching robots a variety of tasks. Diffusion Policy, which uses a conditional denoising diffusion process to generate actions, has demonstrated superior performance, particularly in learning from multi-modal demonstrates. However, it relies on executing multiple actions to retain performance and prevent mode bouncing, which limits its responsiveness,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12724v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12724v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12724v1-abstract-full" style="display: none;"> Imitation learning is an efficient method for teaching robots a variety of tasks. Diffusion Policy, which uses a conditional denoising diffusion process to generate actions, has demonstrated superior performance, particularly in learning from multi-modal demonstrates. However, it relies on executing multiple actions to retain performance and prevent mode bouncing, which limits its responsiveness, as actions are not conditioned on the most recent observations. To address this, we introduce Responsive Noise-Relaying Diffusion Policy (RNR-DP), which maintains a noise-relaying buffer with progressively increasing noise levels and employs a sequential denoising mechanism that generates immediate, noise-free actions at the head of the sequence, while appending noisy actions at the tail. This ensures that actions are responsive and conditioned on the latest observations, while maintaining motion consistency through the noise-relaying buffer. This design enables the handling of tasks requiring responsive control, and accelerates action generation by reusing denoising steps. Experiments on response-sensitive tasks demonstrate that, compared to Diffusion Policy, ours achieves 18% improvement in success rate. Further evaluation on regular tasks demonstrates that RNR-DP also exceeds the best acceleration method by 6.9%, highlighting its computational efficiency advantage in scenarios where responsiveness is less critical. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12724v1-abstract-full').style.display = 'none'; document.getElementById('2502.12724v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12654">arXiv:2502.12654</a> <span> [<a href="https://arxiv.org/pdf/2502.12654">pdf</a>, <a href="https://arxiv.org/ps/2502.12654">ps</a>, <a href="https://arxiv.org/format/2502.12654">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Free Energy and Network Structure: Breaking Scale-Free Behaviour Through Information Processing Constraints </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Williams%2C+P+R">Peter R Williams</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan 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="2502.12654v1-abstract-short" style="display: inline;"> In this paper we show how The Free Energy Principle (FEP) can provide an explanation for why real-world networks deviate from scale-free behaviour, and how these characteristic deviations can emerge from constraints on information processing. We propose a minimal FEP model for node behaviour reveals three distinct regimes: when detection noise dominates, agents seek better information, reducing is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12654v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12654v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12654v1-abstract-full" style="display: none;"> In this paper we show how The Free Energy Principle (FEP) can provide an explanation for why real-world networks deviate from scale-free behaviour, and how these characteristic deviations can emerge from constraints on information processing. We propose a minimal FEP model for node behaviour reveals three distinct regimes: when detection noise dominates, agents seek better information, reducing isolated agents compared to expectations from classical preferential attachment. In the optimal detection regime, super-linear growth emerges from compounded improvements in detection, belief, and action, which produce a preferred cluster scale. Finally, saturation effects occur as limits on the agent's information processing capabilities prevent indefinite cluster growth. These regimes produce the knee-shaped degree distributions observed in real networks, explaining them as signatures of agents with optimal information processing under constraints. We show that agents evolving under FEP principles provides a mechanism for preferential attachment, connecting agent psychology with the macroscopic network features that underpin the structure of real-world networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12654v1-abstract-full').style.display = 'none'; document.getElementById('2502.12654v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12608">arXiv:2502.12608</a> <span> [<a href="https://arxiv.org/pdf/2502.12608">pdf</a>, <a href="https://arxiv.org/format/2502.12608">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"> Unveiling Mode Connectivity in Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Li%2C+B">Bingheng Li</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhikai Chen</a>, <a href="/search/?searchtype=author&query=Han%2C+H">Haoyu Han</a>, <a href="/search/?searchtype=author&query=Zeng%2C+S">Shenglai Zeng</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Jingzhe Liu</a>, <a href="/search/?searchtype=author&query=Tang%2C+J">Jiliang Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.12608v1-abstract-short" style="display: inline;"> A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity, a lens for analyzing geometric properties of loss landscapes has proven insightful for other deep learning architectures, its implications for GNNs remain unexplored. Th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12608v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12608v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12608v1-abstract-full" style="display: none;"> A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity, a lens for analyzing geometric properties of loss landscapes has proven insightful for other deep learning architectures, its implications for GNNs remain unexplored. This work presents the first investigation of mode connectivity in GNNs. We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs. Crucially, we demonstrate that graph structure, rather than model architecture, dominates this behavior, with graph properties like homophily correlating with mode connectivity patterns. We further establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool. Our findings further bridge theoretical insights with practical implications: they rationalize domain alignment strategies in graph learning and provide a foundation for refining GNN training paradigms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12608v1-abstract-full').style.display = 'none'; document.getElementById('2502.12608v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12409">arXiv:2502.12409</a> <span> [<a href="https://arxiv.org/pdf/2502.12409">pdf</a>, <a href="https://arxiv.org/format/2502.12409">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Astrophysics of Galaxies">astro-ph.GA</span> </div> </div> <p class="title is-5 mathjax"> Dominant Role of Coplanar Inflows in Driving Disk Evolution Revealed by Gas-Phase Metallicity Gradients </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lyu%2C+C">Cheqiu Lyu</a>, <a href="/search/?searchtype=author&query=Wang%2C+E">Enci Wang</a>, <a href="/search/?searchtype=author&query=Zhang%2C+H">Hongxin Zhang</a>, <a href="/search/?searchtype=author&query=Peng%2C+Y">Yingjie Peng</a>, <a href="/search/?searchtype=author&query=Wang%2C+X">Xin Wang</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Haixin Li</a>, <a href="/search/?searchtype=author&query=Ma%2C+C">Chengyu Ma</a>, <a href="/search/?searchtype=author&query=Yu%2C+H">Haoran Yu</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zeyu Chen</a>, <a href="/search/?searchtype=author&query=Jia%2C+C">Cheng Jia</a>, <a href="/search/?searchtype=author&query=Kong%2C+X">Xu Kong</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="2502.12409v1-abstract-short" style="display: inline;"> Using spatially resolved spectroscopic data from the MaNGA sample, we investigate the parameters influencing the radial gradients of gas-phase metallicity ($\nabla\log(\mathrm{O/H})$), to determine whether disk formation is primarily driven by coplanar gas inflow or by the independent evolution of distinct regions within the disk. Our results show that $\nabla \log(\mathrm{O/H})$ strongly correlat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12409v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12409v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12409v1-abstract-full" style="display: none;"> Using spatially resolved spectroscopic data from the MaNGA sample, we investigate the parameters influencing the radial gradients of gas-phase metallicity ($\nabla\log(\mathrm{O/H})$), to determine whether disk formation is primarily driven by coplanar gas inflow or by the independent evolution of distinct regions within the disk. Our results show that $\nabla \log(\mathrm{O/H})$ strongly correlates with local gas-phase metallicity at a given stellar mass, with steeper gradients observed in metal-poorer disks. This trend supports the coplanar gas inflow scenario, wherein the gas is progressively enriched by in situ star formation as it flows inward. In contrast, the radial gradient of stellar mass surface density shows very weak correlations with $\nabla \log(\mathrm{O/H})$, which is inconsistent with the independent evolution mode, where gas inflow, star formation, and metal enrichment occur independently within each annulus of the disk. Furthermore, we find that $\nabla \log(\mathrm{O/H})$ is also closely correlated with an indicator of local gas turbulence $蟽_{\mathrm{gas}}/R_{\mathrm{e}}$, highlighting the competing roles of turbulence and coplanar inflow in shaping metallicity gradients. Our results provide indirect observational evidence supporting coplanar gas inflow as the driving mechanism for disk evolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12409v1-abstract-full').style.display = 'none'; document.getElementById('2502.12409v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">16 pages, 5+4 figures. Accepted by ApJL</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12384">arXiv:2502.12384</a> <span> [<a href="https://arxiv.org/pdf/2502.12384">pdf</a>, <a href="https://arxiv.org/format/2502.12384">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhao%2C+Y">Yequan Zhao</a>, <a href="/search/?searchtype=author&query=Yu%2C+X">Xinling Yu</a>, <a href="/search/?searchtype=author&query=Xiao%2C+X">Xian Xiao</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhixiong Chen</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Ziyue Liu</a>, <a href="/search/?searchtype=author&query=Kurczveil%2C+G">Geza Kurczveil</a>, <a href="/search/?searchtype=author&query=Beausoleil%2C+R+G">Raymond G. Beausoleil</a>, <a href="/search/?searchtype=author&query=Liu%2C+S">Sijia Liu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zheng 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="2502.12384v1-abstract-short" style="display: inline;"> Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs), with growing interest in their energy-efficient, real-time training on edge devices. Photonic computing offers a potential solution to achieve this goal because of its ultra-high operation speed. However, the lack of photonic memory and the large device sizes prevent training real-size PIN… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12384v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12384v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12384v1-abstract-full" style="display: none;"> Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs), with growing interest in their energy-efficient, real-time training on edge devices. Photonic computing offers a potential solution to achieve this goal because of its ultra-high operation speed. However, the lack of photonic memory and the large device sizes prevent training real-size PINNs on photonic chips. This paper proposes a completely back-propagation-free (BP-free) and highly salable framework for training real-size PINNs on silicon photonic platforms. Our approach involves three key innovations: (1) a sparse-grid Stein derivative estimator to avoid the BP in the loss evaluation of a PINN, (2) a dimension-reduced zeroth-order optimization via tensor-train decomposition to achieve better scalability and convergence in BP-free training, and (3) a scalable on-chip photonic PINN training accelerator design using photonic tensor cores. We validate our numerical methods on both low- and high-dimensional PDE benchmarks. Through circuit simulation based on real device parameters, we further demonstrate the significant performance benefit (e.g., real-time training, huge chip area reduction) of our photonic accelerator. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12384v1-abstract-full').style.display = 'none'; document.getElementById('2502.12384v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12188">arXiv:2502.12188</a> <span> [<a href="https://arxiv.org/pdf/2502.12188">pdf</a>, <a href="https://arxiv.org/format/2502.12188">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"> Boosting Generalization in Diffusion-Based Neural Combinatorial Solver via Energy-guided Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lei%2C+H">Haoyu Lei</a>, <a href="/search/?searchtype=author&query=Zhou%2C+K">Kaiwen Zhou</a>, <a href="/search/?searchtype=author&query=Li%2C+Y">Yinchuan Li</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhitang Chen</a>, <a href="/search/?searchtype=author&query=Farnia%2C+F">Farzan Farnia</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="2502.12188v1-abstract-short" style="display: inline;"> Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12188v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12188v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12188v1-abstract-full" style="display: none;"> Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditional solvers. While recent studies have introduced training-free guidance approaches that leverage pre-defined guidance functions for zero-shot conditional generation, such methodologies have not been extensively explored in combinatorial optimization. To bridge this gap, we propose a general energy-guided sampling framework during inference time that enhances both the cross-scale and cross-problem generalization capabilities of diffusion-based NCO solvers without requiring additional training. We provide theoretical analysis that helps understanding the cross-problem transfer capability. Our experimental results demonstrate that a diffusion solver, trained exclusively on the Traveling Salesman Problem (TSP), can achieve competitive zero-shot solution generation on TSP variants, such as Prize Collecting TSP (PCTSP) and the Orienteering Problem (OP), through energy-guided sampling across different problem scales. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12188v1-abstract-full').style.display = 'none'; document.getElementById('2502.12188v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12167">arXiv:2502.12167</a> <span> [<a href="https://arxiv.org/pdf/2502.12167">pdf</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"> TastepepAI, An artificial intelligence platform for taste peptide de novo design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yue%2C+J">Jianda Yue</a>, <a href="/search/?searchtype=author&query=Li%2C+T">Tingting Li</a>, <a href="/search/?searchtype=author&query=Ouyang%2C+J">Jian Ouyang</a>, <a href="/search/?searchtype=author&query=Xu%2C+J">Jiawei Xu</a>, <a href="/search/?searchtype=author&query=Tan%2C+H">Hua Tan</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zihui Chen</a>, <a href="/search/?searchtype=author&query=Han%2C+C">Changsheng Han</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Huanyu Li</a>, <a href="/search/?searchtype=author&query=Liang%2C+S">Songping Liang</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Zhonghua Liu</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Zhonghua Liu</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Ying 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="2502.12167v1-abstract-short" style="display: inline;"> Taste peptides have emerged as promising natural flavoring agents attributed to their unique organoleptic properties, high safety profile, and potential health benefits. However, the de novo identification of taste peptides derived from animal, plant, or microbial sources remains a time-consuming and resource-intensive process, significantly impeding their widespread application in the food indust… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12167v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12167v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12167v1-abstract-full" style="display: none;"> Taste peptides have emerged as promising natural flavoring agents attributed to their unique organoleptic properties, high safety profile, and potential health benefits. However, the de novo identification of taste peptides derived from animal, plant, or microbial sources remains a time-consuming and resource-intensive process, significantly impeding their widespread application in the food industry. Here, we present TastePepAI, a comprehensive artificial intelligence framework for customized taste peptide design and safety assessment. As the key element of this framework, a loss-supervised adaptive variational autoencoder (LA-VAE) is implemented to efficiently optimizes the latent representation of sequences during training and facilitates the generation of target peptides with desired taste profiles. Notably, our model incorporates a novel taste-avoidance mechanism, allowing for selective flavor exclusion. Subsequently, our in-house developed toxicity prediction algorithm (SpepToxPred) is integrated in the framework to undergo rigorous safety evaluation of generated peptides. Using this integrated platform, we successfully identified 73 peptides exhibiting sweet, salty, and umami, significantly expanding the current repertoire of taste peptides. This work demonstrates the potential of TastePepAI in accelerating taste peptide discovery for food applications and provides a versatile framework adaptable to broader peptide engineering challenges. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12167v1-abstract-full').style.display = 'none'; document.getElementById('2502.12167v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">40 pages, 6 figures, research article</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.12152">arXiv:2502.12152</a> <span> [<a href="https://arxiv.org/pdf/2502.12152">pdf</a>, <a href="https://arxiv.org/format/2502.12152">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learning Getting-Up Policies for Real-World Humanoid Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=He%2C+X">Xialin He</a>, <a href="/search/?searchtype=author&query=Dong%2C+R">Runpei Dong</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zixuan Chen</a>, <a href="/search/?searchtype=author&query=Gupta%2C+S">Saurabh Gupta</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="2502.12152v1-abstract-short" style="display: inline;"> Automatic fall recovery is a crucial prerequisite before humanoid robots can be reliably deployed. Hand-designing controllers for getting up is difficult because of the varied configurations a humanoid can end up in after a fall and the challenging terrains humanoid robots are expected to operate on. This paper develops a learning framework to produce controllers that enable humanoid robots to get… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12152v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12152v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12152v1-abstract-full" style="display: none;"> Automatic fall recovery is a crucial prerequisite before humanoid robots can be reliably deployed. Hand-designing controllers for getting up is difficult because of the varied configurations a humanoid can end up in after a fall and the challenging terrains humanoid robots are expected to operate on. This paper develops a learning framework to produce controllers that enable humanoid robots to get up from varying configurations on varying terrains. Unlike previous successful applications of humanoid locomotion learning, the getting-up task involves complex contact patterns, which necessitates accurately modeling the collision geometry and sparser rewards. We address these challenges through a two-phase approach that follows a curriculum. The first stage focuses on discovering a good getting-up trajectory under minimal constraints on smoothness or speed / torque limits. The second stage then refines the discovered motions into deployable (i.e. smooth and slow) motions that are robust to variations in initial configuration and terrains. We find these innovations enable a real-world G1 humanoid robot to get up from two main situations that we considered: a) lying face up and b) lying face down, both tested on flat, deformable, slippery surfaces and slopes (e.g., sloppy grass and snowfield). To the best of our knowledge, this is the first successful demonstration of learned getting-up policies for human-sized humanoid robots in the real world. Project page: https://humanoid-getup.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12152v1-abstract-full').style.display = 'none'; document.getElementById('2502.12152v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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://humanoid-getup.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/2502.12130">arXiv:2502.12130</a> <span> [<a href="https://arxiv.org/pdf/2502.12130">pdf</a>, <a href="https://arxiv.org/format/2502.12130">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"> Scaling Autonomous Agents via Automatic Reward Modeling And Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhenfang Chen</a>, <a href="/search/?searchtype=author&query=Chen%2C+D">Delin Chen</a>, <a href="/search/?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/?searchtype=author&query=Liu%2C+W">Wenjun Liu</a>, <a href="/search/?searchtype=author&query=Gan%2C+C">Chuang Gan</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="2502.12130v1-abstract-short" style="display: inline;"> Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online shopping, scientific reasoning, and mathematical problem-solving. Unlike pure text data, collecting large-scale decision-making data is challenging. Moreover, many p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12130v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12130v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12130v1-abstract-full" style="display: none;"> Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online shopping, scientific reasoning, and mathematical problem-solving. Unlike pure text data, collecting large-scale decision-making data is challenging. Moreover, many powerful LLMs are only accessible through APIs, which hinders their fine-tuning for agent tasks due to cost and complexity. To address LLM agents' limitations, we propose a framework that can automatically learn a reward model from the environment without human annotations. This model can be used to evaluate the action trajectories of LLM agents and provide heuristics for task planning. Specifically, our approach involves employing one LLM-based agent to navigate an environment randomly, generating diverse action trajectories. Subsequently, a separate LLM is leveraged to assign a task intent and synthesize a negative response alongside the correct response for each trajectory. These triplets (task intent, positive response, and negative response) are then utilized as training data to optimize a reward model capable of scoring action trajectories. The effectiveness and generalizability of our framework are demonstrated through evaluations conducted on different agent benchmarks. In conclusion, our proposed framework represents a significant advancement in enhancing LLM agents' decision-making capabilities. By automating the learning of reward models, we overcome the challenges of data scarcity and API limitations, potentially revolutionizing the application of LLMs in complex and interactive environments. This research paves the way for more sophisticated AI agents capable of tackling a wide range of real-world problems requiring multi-step decision-making. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12130v1-abstract-full').style.display = 'none'; document.getElementById('2502.12130v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">ICLR2025, Project page: https://armap-agent.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/2502.12022">arXiv:2502.12022</a> <span> [<a href="https://arxiv.org/pdf/2502.12022">pdf</a>, <a href="https://arxiv.org/format/2502.12022">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"> Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+X">Xin Xu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Y">Yan Xu</a>, <a href="/search/?searchtype=author&query=Chen%2C+T">Tianhao Chen</a>, <a href="/search/?searchtype=author&query=Yan%2C+Y">Yuchen Yan</a>, <a href="/search/?searchtype=author&query=Liu%2C+C">Chengwu Liu</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zaoyu Chen</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yufei Wang</a>, <a href="/search/?searchtype=author&query=Yin%2C+Y">Yichun Yin</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yasheng Wang</a>, <a href="/search/?searchtype=author&query=Shang%2C+L">Lifeng Shang</a>, <a href="/search/?searchtype=author&query=Liu%2C+Q">Qun 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="2502.12022v1-abstract-short" style="display: inline;"> Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these methods, they primarily rely on post-selection or predefined strategies, leaving an open question: whether LLMs can autonomously adapt their reasoning strategy ba… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12022v1-abstract-full').style.display = 'inline'; document.getElementById('2502.12022v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.12022v1-abstract-full" style="display: none;"> Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these methods, they primarily rely on post-selection or predefined strategies, leaving an open question: whether LLMs can autonomously adapt their reasoning strategy based on their inherent capabilities. In this work, we propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously, aligning it with their intrinsic aptitude. TATA incorporates base-LLM-aware data selection during supervised fine-tuning (SFT) to tailor training data to the model's unique abilities. This approach equips LLMs to autonomously determine and apply the appropriate reasoning strategy at test time. We evaluate TATA through extensive experiments on six mathematical reasoning benchmarks, using both general-purpose and math-specialized LLMs. Empirical results demonstrate that TATA effectively combines the complementary strengths of CoT and TIR, achieving superior or comparable performance with improved inference efficiency compared to TIR alone. Further analysis underscores the critical role of aptitude-aware data selection in enabling LLMs to make effective and adaptive reasoning decisions and align reasoning strategies with model capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.12022v1-abstract-full').style.display = 'none'; document.getElementById('2502.12022v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11729">arXiv:2502.11729</a> <span> [<a href="https://arxiv.org/pdf/2502.11729">pdf</a>, <a href="https://arxiv.org/format/2502.11729">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> </div> </div> <p class="title is-5 mathjax"> On Quantizing Neural Representation for Variable-Rate Video Coding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Shi%2C+J">Junqi Shi</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhujia Chen</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Hanfei Li</a>, <a href="/search/?searchtype=author&query=Zhao%2C+Q">Qi Zhao</a>, <a href="/search/?searchtype=author&query=Lu%2C+M">Ming Lu</a>, <a href="/search/?searchtype=author&query=Chen%2C+T">Tong Chen</a>, <a href="/search/?searchtype=author&query=Ma%2C+Z">Zhan Ma</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="2502.11729v1-abstract-short" style="display: inline;"> This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight retraining for each target bitrate, we hypothesize that variable-rate coding can be achieved by adjusting quantization parameters (QPs) of pre-trained weights. Ou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11729v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11729v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11729v1-abstract-full" style="display: none;"> This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight retraining for each target bitrate, we hypothesize that variable-rate coding can be achieved by adjusting quantization parameters (QPs) of pre-trained weights. Our study reveals that traditional quantization methods, which assume inter-layer independence, are ineffective for non-generalized INR-VC models due to significant dependencies across layers. To address this, we redefine variable-rate INR-VC as a mixed-precision quantization problem and establish a theoretical framework for sensitivity criteria aimed at simplified, fine-grained rate control. Additionally, we propose network-wise calibration and channel-wise quantization strategies to minimize quantization-induced errors, arriving at a unified formula for representation-oriented PTQ calibration. Our experimental evaluations demonstrate that NeuroQuant significantly outperforms existing techniques in varying bitwidth quantization and compression efficiency, accelerating encoding by up to eight times and enabling quantization down to INT2 with minimal reconstruction loss. This work introduces variable-rate INR-VC for the first time and lays a theoretical foundation for future research in rate-distortion optimization, advancing the field of video coding technology. The materials will be available at https://github.com/Eric-qi/NeuroQuant. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11729v1-abstract-full').style.display = 'none'; document.getElementById('2502.11729v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 be pulished in ICLR'25</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11724">arXiv:2502.11724</a> <span> [<a href="https://arxiv.org/pdf/2502.11724">pdf</a>, <a href="https://arxiv.org/format/2502.11724">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"> Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+C">Chengzhi Liu</a>, <a href="/search/?searchtype=author&query=Huang%2C+Z">Zile Huang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhe Chen</a>, <a href="/search/?searchtype=author&query=Tang%2C+F">Feilong Tang</a>, <a href="/search/?searchtype=author&query=Tian%2C+Y">Yu Tian</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhongxing Xu</a>, <a href="/search/?searchtype=author&query=Luo%2C+Z">Zihong Luo</a>, <a href="/search/?searchtype=author&query=Zheng%2C+Y">Yalin Zheng</a>, <a href="/search/?searchtype=author&query=Meng%2C+Y">Yanda Meng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.11724v1-abstract-short" style="display: inline;"> Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in real-world scenarios. Existing deep learning methods tend to address it by learning an implicit latent subspace representation for different modality combinations.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11724v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11724v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11724v1-abstract-full" style="display: none;"> Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in real-world scenarios. Existing deep learning methods tend to address it by learning an implicit latent subspace representation for different modality combinations. We identify two significant limitations of these methods: (1) implicit representation constraints that hinder the model's ability to capture modality-specific information and (2) modality heterogeneity, causing distribution gaps and redundancy in feature representations. To address these, we propose an Incomplete Modality Disentangled Representation (IMDR) strategy, which disentangles features into explicit independent modal-common and modal-specific features by guidance of mutual information, distilling informative knowledge and enabling it to reconstruct valuable missing semantics and produce robust multimodal representations. Furthermore, we introduce a joint proxy learning module that assists IMDR in eliminating intra-modality redundancy by exploiting the extracted proxies from each class. Experiments on four ophthalmology multimodal datasets demonstrate that the proposed IMDR outperforms the state-of-the-art methods significantly. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11724v1-abstract-full').style.display = 'none'; document.getElementById('2502.11724v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 Pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> AAAI2025 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11381">arXiv:2502.11381</a> <span> [<a href="https://arxiv.org/pdf/2502.11381">pdf</a>, <a href="https://arxiv.org/format/2502.11381">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"> Without Paired Labeled Data: An End-to-End Self-Supervised Paradigm for UAV-View Geo-Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhongwei Chen</a>, <a href="/search/?searchtype=author&query=Yang%2C+Z">Zhao-Xu Yang</a>, <a href="/search/?searchtype=author&query=Rong%2C+H">Hai-Jun Rong</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="2502.11381v1-abstract-short" style="display: inline;"> UAV-View Geo-Localization (UVGL) aims to ascertain the precise location of a UAV by retrieving the most similar GPS-tagged satellite image. However, existing methods predominantly rely on supervised learning paradigms that necessitate annotated paired data for training, which incurs substantial annotation costs and impedes large-scale deployment. To overcome this limitation, we propose the Dynamic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11381v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11381v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11381v1-abstract-full" style="display: none;"> UAV-View Geo-Localization (UVGL) aims to ascertain the precise location of a UAV by retrieving the most similar GPS-tagged satellite image. However, existing methods predominantly rely on supervised learning paradigms that necessitate annotated paired data for training, which incurs substantial annotation costs and impedes large-scale deployment. To overcome this limitation, we propose the Dynamic Memory-Driven and Neighborhood Information Learning (DMNIL) network, a lightweight end-to-end self-supervised framework for UAV-view geo-localization. The DMNIL framework utilizes a dual-path clustering-based contrastive learning architecture as its baseline to model intra-view structural relationships, enhancing feature consistency and discriminability. Additionally, a dynamic memory-driven hierarchical learning module is proposed to progressively mine local and global information, reinforcing multi-level feature associations to improve model robustness. To bridge the domain gap between UAV and satellite views, we design an information-consistent evolutionary learning mechanism that systematically explores latent correlations within intra-view neighborhoods and across cross-view domains, ultimately constructing a unified cross-view feature representation space. Extensive experiments on three benchmarks (University-1652, SUES-200, and DenseUAV) demonstrate that DMNIL achieves competitive performance against state-of-the-art supervised methods while maintaining computational efficiency. Notably, this superiority is attained without relying on paired training data, underscoring the framework's practicality for real-world deployment. Codes will be released soon. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11381v1-abstract-full').style.display = 'none'; document.getElementById('2502.11381v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11372">arXiv:2502.11372</a> <span> [<a href="https://arxiv.org/pdf/2502.11372">pdf</a>, <a href="https://arxiv.org/format/2502.11372">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Weibull Processes in Network Degree Distributions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Williams%2C+P+R">Peter R Williams</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan 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="2502.11372v1-abstract-short" style="display: inline;"> This study examines degree distributions in two large collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020), comprising $2.72 \times 10^8$ and $1.88 \times 10^6$ nodes respectively. Statistical comparison using $蠂^2$ measures showed that Weibull distributions fit the degree distributions better than power-law or log-normal models, especially at la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11372v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11372v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11372v1-abstract-full" style="display: none;"> This study examines degree distributions in two large collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020), comprising $2.72 \times 10^8$ and $1.88 \times 10^6$ nodes respectively. Statistical comparison using $蠂^2$ measures showed that Weibull distributions fit the degree distributions better than power-law or log-normal models, especially at later stages in the network evolution. The Weibull shape parameters exhibit notable stability ($k \approx 0.8$-$1.0$ for academic, $k \approx 0.9$-$1.1$ for entertainment collaborations) despite orders of magnitude growth in network size. While early-stage networks display approximate power-law scaling, mature networks develop characteristic flattening in the low-degree region that Weibull distributions appear to capture better. In the academic network, the cutoff between the flattened region and power-law tail shows a gradual increase from $5$ to $9$ edges over time, while the entertainment network maintains a distinctive degree structure that may reflect storytelling and cast-size constraints. These patterns suggest the possibility that collaboration network evolution might be influenced more by constraint-based growth than by pure preferential attachment or multiplicative processes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11372v1-abstract-full').style.display = 'none'; document.getElementById('2502.11372v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11315">arXiv:2502.11315</a> <span> [<a href="https://arxiv.org/pdf/2502.11315">pdf</a>, <a href="https://arxiv.org/format/2502.11315">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Soft Condensed Matter">cond-mat.soft</span> </div> </div> <p class="title is-5 mathjax"> Microscopic contact line dynamics dictate the emergent behaviors of particle rafts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Mukherjee%2C+R">Ranit Mukherjee</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zih-Yin Chen</a>, <a href="/search/?searchtype=author&query=Cheng%2C+X">Xiang Cheng</a>, <a href="/search/?searchtype=author&query=Lee%2C+S">Sungyon Lee</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="2502.11315v1-abstract-short" style="display: inline;"> Fluid-fluid interfaces laden with discrete particles behave curiously like continuous elastic sheets, leading to their applications in emulsion and foam stabilization. Although existing continuum models can qualitatively capture the elastic buckling of these particle-laden interfaces -- often referred to as particle rafts -- under compression, they fail to link their macroscopic collective propert… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11315v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11315v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11315v1-abstract-full" style="display: none;"> Fluid-fluid interfaces laden with discrete particles behave curiously like continuous elastic sheets, leading to their applications in emulsion and foam stabilization. Although existing continuum models can qualitatively capture the elastic buckling of these particle-laden interfaces -- often referred to as particle rafts -- under compression, they fail to link their macroscopic collective properties to the microscopic behaviors of individual particles. Thus, phenomena such as particle expulsion from the compressed rafts remain unexplained. Here, by combining systematic experiments with first-principle modeling, we reveal how the macroscopic mechanical properties of particle rafts emerge from particle-scale interactions. We construct a phase diagram that delineates the conditions under which a particle raft collapses via collective folding versus single-particle expulsion. Guided by this theoretical framework, we demonstrate control over the raft's failure mode by tuning the physicochemical properties of individual particles. Our study highlights the previously overlooked dual nature of particle rafts and exemplifies how collective dynamics can arise from discrete components with simple interactions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11315v1-abstract-full').style.display = 'none'; document.getElementById('2502.11315v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">13 pages, 9 figures (in review in Physical Review Letters)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11248">arXiv:2502.11248</a> <span> [<a href="https://arxiv.org/pdf/2502.11248">pdf</a>, <a href="https://arxiv.org/format/2502.11248">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Prevalence, Sharing Patterns, and Spreaders of Multimodal AI-Generated Content on X during the 2024 U.S. Presidential Election </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhiyi Chen</a>, <a href="/search/?searchtype=author&query=Ye%2C+J">Jinyi Ye</a>, <a href="/search/?searchtype=author&query=Ferrara%2C+E">Emilio Ferrara</a>, <a href="/search/?searchtype=author&query=Luceri%2C+L">Luca Luceri</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="2502.11248v1-abstract-short" style="display: inline;"> While concerns about the risks of AI-generated content (AIGC) to the integrity of social media discussions have been raised, little is known about its scale and the actors responsible for its dissemination online. In this work, we identify and characterize the prevalence, sharing patterns, and spreaders of AIGC in different modalities, including images and texts. Analyzing a large-scale dataset fr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11248v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11248v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11248v1-abstract-full" style="display: none;"> While concerns about the risks of AI-generated content (AIGC) to the integrity of social media discussions have been raised, little is known about its scale and the actors responsible for its dissemination online. In this work, we identify and characterize the prevalence, sharing patterns, and spreaders of AIGC in different modalities, including images and texts. Analyzing a large-scale dataset from X related to the 2024 U.S. Presidential Election, we find that approximately 12% of images and 1.4% of texts are deemed AI-generated. Notably, roughly 3% of text spreaders and 10% of image spreaders account for 80% of the AI-generated content within their respective modalities. Superspreaders of AIGC are more likely to be X Premium subscribers with a right-leaning orientation and exhibit automated behavior. Additionally, AI image spreaders have a higher proportion of AI-generated content in their profiles compared to AI text spreaders. This study serves as a very first step toward understanding the role generative AI plays in shaping online socio-political environments and offers implications for platform governance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11248v1-abstract-full').style.display = 'none'; document.getElementById('2502.11248v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11160">arXiv:2502.11160</a> <span> [<a href="https://arxiv.org/pdf/2502.11160">pdf</a>, <a href="https://arxiv.org/format/2502.11160">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cosmology and Nongalactic Astrophysics">astro-ph.CO</span> </div> </div> <p class="title is-5 mathjax"> CSST Cosmological Emulator I: Matter Power Spectrum Emulation with one percent accuracy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhao Chen</a>, <a href="/search/?searchtype=author&query=Yu%2C+Y">Yu Yu</a>, <a href="/search/?searchtype=author&query=Han%2C+J">Jiaxin Han</a>, <a href="/search/?searchtype=author&query=Jing%2C+Y+P">Y. P. Jing</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="2502.11160v1-abstract-short" style="display: inline;"> In the near future, the China Space Station Telescope (CSST) will obtain unprecedented imaging and spectroscopic data. The statistical errors in the cosmological parameter constraints will be reduced significantly. The corresponding theoretical tools must meet the percent-level accuracy required to extract as much cosmological information as possible from the observations. We present the \texttt{C… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11160v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11160v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11160v1-abstract-full" style="display: none;"> In the near future, the China Space Station Telescope (CSST) will obtain unprecedented imaging and spectroscopic data. The statistical errors in the cosmological parameter constraints will be reduced significantly. The corresponding theoretical tools must meet the percent-level accuracy required to extract as much cosmological information as possible from the observations. We present the \texttt{CSST Emulator} to provide nonlinear power spectrum predictions in the eight cosmological parameter space $惟_\mathrm{cb},惟_\mathrm{b},H_{0},n_{s},A_{s},w_{0}, w_{a}$, and $m_谓$. It is constructed based on the \textsc{Kun} simulation suite, consisting of 129 high-resolution simulations with box size $L=1\,h^{-1} {\rm Gpc}$ and evolving $3072^3$ particles. The determinations of parameter ranges, sampling method, and emulation strategy in the whole construction have been optimized exquisitely. This enables our prediction for $k\leq 10\,h {\rm Mpc}^{-1}$ and $z\leq 2.0$ to reach $1\%$ accuracy validated through internal and external simulations. We also compare our results with recent \texttt{BACCO}, \texttt{EuclidEmulator2}, and \texttt{Mira-Titan IV} emulators, which demonstrate the \texttt{CSST Emulator}'s excellent performance across a wide cosmological parameter range in the nonlinear regime. \texttt{CSST Emulator} is publicly released at https://github.com/czymh/csstemu, and provides a fundamental theoretical tool for accurate cosmological inference with future CSST observations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11160v1-abstract-full').style.display = 'none'; document.getElementById('2502.11160v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">CSST Emulator is publicly released at https://github.com/czymh/csstemu. 18+2 pages, 11+4 figures, comments are welcomed!</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11156">arXiv:2502.11156</a> <span> [<a href="https://arxiv.org/pdf/2502.11156">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> </div> </div> <p class="title is-5 mathjax"> DLBayesian: An Alternative Bayesian Reconstruction of Limited-view CT by Optimizing Deep Learning Parameters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+C">Changyu Chen</a>, <a href="/search/?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/?searchtype=author&query=Xing%2C+Y">Yuxiang Xing</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhiqiang 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="2502.11156v1-abstract-short" style="display: inline;"> Limited-view computed tomography (CT) presents significant potential for reducing radiation exposure and expediting the scanning process. While deep learning (DL) methods have exhibited promising results in mitigating streaking artifacts caused by a reduced number of projection views, their generalization remains challenging. In this work, we proposed a DL-driven alternative Bayesian reconstructio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11156v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11156v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11156v1-abstract-full" style="display: none;"> Limited-view computed tomography (CT) presents significant potential for reducing radiation exposure and expediting the scanning process. While deep learning (DL) methods have exhibited promising results in mitigating streaking artifacts caused by a reduced number of projection views, their generalization remains challenging. In this work, we proposed a DL-driven alternative Bayesian reconstruction method (DLBayesian) that efficiently integrates data-driven priors and data consistency constraints. DLBayesian comprises three stages: group-level embedding, significance evaluation, and individual-level consistency adaptation. Firstly, DL network parameters are optimized to learn how to eliminate the general limited-view artifacts on a large-scale paired dataset. Then, we introduced a significance score to quantitatively evaluate the contribution of parameters in DL models as a guide for the subsequent individual-level adaptation. Finally, in the Bayesian adaptation stage, an alternative Bayesian reconstruction further optimizes the DL network parameters precisely according to the projection data of the target case. We validated DLBayesian with sparse-view (90 views) projections from a circular trajectory CT and a special data missing case from a multi-segment linear trajectory CT. The results underscore DLBayesian's superior generalization capabilities across variations in patients, anatomic structures, and data distribution, as well as excelling in contextual structure recovery compared to networks solely trained via supervised loss. Real experiments on a dead rat demonstrate its capability in practical CT scans. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11156v1-abstract-full').style.display = 'none'; document.getElementById('2502.11156v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11112">arXiv:2502.11112</a> <span> [<a href="https://arxiv.org/pdf/2502.11112">pdf</a>, <a href="https://arxiv.org/format/2502.11112">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Parametric Analysis of Network Evolution Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Williams%2C+P">Peter Williams</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan 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="2502.11112v1-abstract-short" style="display: inline;"> We present a comprehensive parametric analysis of node and edge lifetimes processes in two large-scale collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020). Node and edge lifetimes (career and collaboration durations) follow Weibull distributions with consistent shape parameters ($k \approx 0.2$ for academic, $k \approx 0.5$ for entertainment car… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11112v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11112v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11112v1-abstract-full" style="display: none;"> We present a comprehensive parametric analysis of node and edge lifetimes processes in two large-scale collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020). Node and edge lifetimes (career and collaboration durations) follow Weibull distributions with consistent shape parameters ($k \approx 0.2$ for academic, $k \approx 0.5$ for entertainment careers) across centuries of evolution. These distributions persist despite dramatic changes in network size and structure. Edge processes show domain-specific evolution: academic collaboration durations increase over time (power-law index $1.6$ to $2.3$) while entertainment collaborations maintain more stable patterns (index $2.6$ to $2.1$). These findings indicate that while career longevity exhibits consistent patterns, collaboration dynamics appear to be influenced by domain-specific factors. The results provide new constraints for models of social network evolution, requiring incorporation of both universal lifetime distributions and domain-specific growth dynamics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11112v1-abstract-full').style.display = 'none'; document.getElementById('2502.11112v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11109">arXiv:2502.11109</a> <span> [<a href="https://arxiv.org/pdf/2502.11109">pdf</a>, <a href="https://arxiv.org/format/2502.11109">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Explosive Growth in Large-Scale Collaboration Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Williams%2C+P">Peter Williams</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhan 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="2502.11109v1-abstract-short" style="display: inline;"> We analyse the evolution of two large collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020), comprising $2.72 \times 10^8$ and $1.88 \times 10^6$ nodes respectively. The networks show super-linear growth, with node counts following power laws $N(t) \propto t^伪$ where $伪= 2.3$ increasing to $3.1$ after 1950 (MAG) and $伪= 1.8$ (IMDb). Node and edge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11109v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11109v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11109v1-abstract-full" style="display: none;"> We analyse the evolution of two large collaboration networks: the Microsoft Academic Graph (1800-2020) and Internet Movie Database (1900-2020), comprising $2.72 \times 10^8$ and $1.88 \times 10^6$ nodes respectively. The networks show super-linear growth, with node counts following power laws $N(t) \propto t^伪$ where $伪= 2.3$ increasing to $3.1$ after 1950 (MAG) and $伪= 1.8$ (IMDb). Node and edge processes maintain stable but noisy timescale ratios ($蟿_N/蟿_E \approx 2.8 \pm 0.3$ MAG, $2.3 \pm 0.2$ IMDb). The probability of waiting a time $t$ between successive collaborations was found to be scale-free, $P(t) \propto t^{-纬}$, with indices evolving from $纬\approx 2.3$ to $1.6$ (MAG) and $2.6$ to $2.1$ (IMDb). Academic collaboration sizes increased from $1.2$ to $5.8$ authors per paper, while entertainment collaborations remained more stable ($3.2$ to $4.5$ actors). These observations indicate that current network models might be enhanced by considering accelerating growth, coupled timescales, and environmental influence, while explaining stable local properties. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11109v1-abstract-full').style.display = 'none'; document.getElementById('2502.11109v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11079">arXiv:2502.11079</a> <span> [<a href="https://arxiv.org/pdf/2502.11079">pdf</a>, <a href="https://arxiv.org/format/2502.11079">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"> Phantom: Subject-consistent video generation via cross-modal alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+L">Lijie Liu</a>, <a href="/search/?searchtype=author&query=Ma%2C+T">Tianxiang Ma</a>, <a href="/search/?searchtype=author&query=Li%2C+B">Bingchuan Li</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhuowei Chen</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Jiawei Liu</a>, <a href="/search/?searchtype=author&query=He%2C+Q">Qian He</a>, <a href="/search/?searchtype=author&query=Wu%2C+X">Xinglong 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="2502.11079v1-abstract-short" style="display: inline;"> The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts subject elements from reference images and generates subject-consistent video through textual instructions. We believe that the essence of subject-to-video lies in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11079v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11079v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11079v1-abstract-full" style="display: none;"> The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts subject elements from reference images and generates subject-consistent video through textual instructions. We believe that the essence of subject-to-video lies in balancing the dual-modal prompts of text and image, thereby deeply and simultaneously aligning both text and visual content. To this end, we propose Phantom, a unified video generation framework for both single and multi-subject references. Building on existing text-to-video and image-to-video architectures, we redesign the joint text-image injection model and drive it to learn cross-modal alignment via text-image-video triplet data. In particular, we emphasize subject consistency in human generation, covering existing ID-preserving video generation while offering enhanced advantages. The project homepage is here https://phantom-video.github.io/Phantom/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11079v1-abstract-full').style.display = 'none'; document.getElementById('2502.11079v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11078">arXiv:2502.11078</a> <span> [<a href="https://arxiv.org/pdf/2502.11078">pdf</a>, <a href="https://arxiv.org/format/2502.11078">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"> DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+A">Aili Chen</a>, <a href="/search/?searchtype=author&query=Du%2C+C">Chengyu Du</a>, <a href="/search/?searchtype=author&query=Chen%2C+J">Jiangjie Chen</a>, <a href="/search/?searchtype=author&query=Xu%2C+J">Jinghan Xu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yikai Zhang</a>, <a href="/search/?searchtype=author&query=Yuan%2C+S">Siyu Yuan</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zulong Chen</a>, <a href="/search/?searchtype=author&query=Li%2C+L">Liangyue Li</a>, <a href="/search/?searchtype=author&query=Xiao%2C+Y">Yanghua Xiao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.11078v1-abstract-short" style="display: inline;"> To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for human -readable persona modeling. In dynamic real -world scenarios, effective persona modeling necessitates leveraging streaming behavior data to continually optimize user personas. However, existing methods -whether regenerating per… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11078v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11078v1-abstract-full" style="display: none;"> To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for human -readable persona modeling. In dynamic real -world scenarios, effective persona modeling necessitates leveraging streaming behavior data to continually optimize user personas. However, existing methods -whether regenerating personas or incrementally extending them with new behaviors -often fail to achieve sustained improvements in persona quality or future behavior prediction accuracy. To address this, we propose DEEPER, a novel approach for dynamic persona modeling that enables continual persona optimization. Specifically, we enhance the model's direction -search capability through an iterative reinforcement learning framework, allowing it to automatically identify effective update directions and optimize personas using discrepancies between user behaviors and model predictions. Extensive experiments on dynamic persona modeling involving 4800 users across 10 domains highlight the superior persona optimization capabilities of DEEPER, delivering an impressive 32.2% average reduction in user behavior prediction error over four update rounds -outperforming the best baseline by a remarkable 22.92%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11078v1-abstract-full').style.display = 'none'; document.getElementById('2502.11078v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11047">arXiv:2502.11047</a> <span> [<a href="https://arxiv.org/pdf/2502.11047">pdf</a>, <a href="https://arxiv.org/ps/2502.11047">ps</a>, <a href="https://arxiv.org/format/2502.11047">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Search for the Cabibbo-suppressed decays $螞_c^{+}\to危^0K^{+}蟺^{0}$ and $螞_c^{+}\to危^0K^{+}蟺^{+}蟺^{-}$ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=BESIII+Collaboration"> BESIII Collaboration</a>, <a href="/search/?searchtype=author&query=Ablikim%2C+M">M. Ablikim</a>, <a href="/search/?searchtype=author&query=Achasov%2C+M+N">M. N. Achasov</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Ai%2C+X+C">X. C. Ai</a>, <a href="/search/?searchtype=author&query=Aliberti%2C+R">R. Aliberti</a>, <a href="/search/?searchtype=author&query=Amoroso%2C+A">A. Amoroso</a>, <a href="/search/?searchtype=author&query=An%2C+Q">Q. An</a>, <a href="/search/?searchtype=author&query=Bai%2C+Y">Y. Bai</a>, <a href="/search/?searchtype=author&query=Bakina%2C+O">O. Bakina</a>, <a href="/search/?searchtype=author&query=Ban%2C+Y">Y. Ban</a>, <a href="/search/?searchtype=author&query=Bao%2C+H+-">H. -R. Bao</a>, <a href="/search/?searchtype=author&query=Batozskaya%2C+V">V. Batozskaya</a>, <a href="/search/?searchtype=author&query=Begzsuren%2C+K">K. Begzsuren</a>, <a href="/search/?searchtype=author&query=Berger%2C+N">N. Berger</a>, <a href="/search/?searchtype=author&query=Berlowski%2C+M">M. Berlowski</a>, <a href="/search/?searchtype=author&query=Bertani%2C+M">M. Bertani</a>, <a href="/search/?searchtype=author&query=Bettoni%2C+D">D. Bettoni</a>, <a href="/search/?searchtype=author&query=Bianchi%2C+F">F. Bianchi</a>, <a href="/search/?searchtype=author&query=Bianco%2C+E">E. Bianco</a>, <a href="/search/?searchtype=author&query=Bortone%2C+A">A. Bortone</a>, <a href="/search/?searchtype=author&query=Boyko%2C+I">I. Boyko</a>, <a href="/search/?searchtype=author&query=Briere%2C+R+A">R. A. Briere</a>, <a href="/search/?searchtype=author&query=Brueggemann%2C+A">A. Brueggemann</a>, <a href="/search/?searchtype=author&query=Cai%2C+H">H. Cai</a> , et al. (687 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="2502.11047v1-abstract-short" style="display: inline;"> Utilizing 4.5 $fb^-$ of $e^+e^-$ annihilation data collected at center-of-mass energies ranging from 4599.53 MeV to 4698.82 MeV by the BESIII detector at the BEPCII collider, we search for the singly Cabibbo-suppressed hadronic decays $螞_{c}^{+}\to危^{0} K^{+}蟺^{0}$ and $螞_{c}^{+}\to危^{0}K^{+}蟺^+蟺^-$ with a single-tag method. No significant signals are observed for both decays. The upper limits on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11047v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11047v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11047v1-abstract-full" style="display: none;"> Utilizing 4.5 $fb^-$ of $e^+e^-$ annihilation data collected at center-of-mass energies ranging from 4599.53 MeV to 4698.82 MeV by the BESIII detector at the BEPCII collider, we search for the singly Cabibbo-suppressed hadronic decays $螞_{c}^{+}\to危^{0} K^{+}蟺^{0}$ and $螞_{c}^{+}\to危^{0}K^{+}蟺^+蟺^-$ with a single-tag method. No significant signals are observed for both decays. The upper limits on the branching fractions at the $90\%$ confidence level are determined to be $5.0\times 10^{-4}$ for $螞_{c}^{+}\to危^{0} K^{+}蟺^{0}$ and $6.5\times 10^{-4}$ for $螞_c^{+}\to危^0K^{+}蟺^{+}蟺^{-}$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11047v1-abstract-full').style.display = 'none'; document.getElementById('2502.11047v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11026">arXiv:2502.11026</a> <span> [<a href="https://arxiv.org/pdf/2502.11026">pdf</a>, <a href="https://arxiv.org/format/2502.11026">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"> Simplify RLHF as Reward-Weighted SFT: A Variational Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Du%2C+Y">Yuhao Du</a>, <a href="/search/?searchtype=author&query=Li%2C+Z">Zhuo Li</a>, <a href="/search/?searchtype=author&query=Cheng%2C+P">Pengyu Cheng</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhihong Chen</a>, <a href="/search/?searchtype=author&query=Xie%2C+Y">Yuejiao Xie</a>, <a href="/search/?searchtype=author&query=Wan%2C+X">Xiang Wan</a>, <a href="/search/?searchtype=author&query=Gao%2C+A">Anningzhe 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="2502.11026v2-abstract-short" style="display: inline;"> Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption. Even with recent simplifications, such as Direct Preference Optimization (DPO) and Advantage Leftover Lunch (A-LoL), the problems of over-fitting and training in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11026v2-abstract-full').style.display = 'inline'; document.getElementById('2502.11026v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11026v2-abstract-full" style="display: none;"> Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption. Even with recent simplifications, such as Direct Preference Optimization (DPO) and Advantage Leftover Lunch (A-LoL), the problems of over-fitting and training instability remain hindering the alignment process from the expected optimal performance. To address the existing challenges, we propose a novel simplification of RLHF from the perspective of variational inference, called $\textbf{V}$ariational $\textbf{A}$lignment with $\textbf{R}$e-weighting ($\textbf{VAR}$). More specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into a reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness. On comprehensive alignment and generation benchmarks, our VAR method has numerically achieved competitive performance in LLM alignment helpfulness and harmlessness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11026v2-abstract-full').style.display = 'none'; document.getElementById('2502.11026v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10967">arXiv:2502.10967</a> <span> [<a href="https://arxiv.org/pdf/2502.10967">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Shen%2C+X">Xiao Shen</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhihao Chen</a>, <a href="/search/?searchtype=author&query=Pan%2C+S">Shirui Pan</a>, <a href="/search/?searchtype=author&query=Zhou%2C+S">Shuang Zhou</a>, <a href="/search/?searchtype=author&query=Yang%2C+L+T">Laurence T. Yang</a>, <a href="/search/?searchtype=author&query=Zhou%2C+X">Xi 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="2502.10967v1-abstract-short" style="display: inline;"> Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network might contain additional classes that are not present in the source. In this work, we study a more realistic open-set cross-network node cl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10967v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10967v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10967v1-abstract-full" style="display: none;"> Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network might contain additional classes that are not present in the source. In this work, we study a more realistic open-set cross-network node classification (O-CNNC) problem, where the target network contains all the known classes in the source and further contains several target-private classes unseen in the source. Borrowing the concept from open-set domain adaptation, all target-private classes are defined as an additional unknown class. To address the challenging O-CNNC problem, we propose an unknown-excluded adversarial graph domain alignment (UAGA) model with a separate-adapt training strategy. Firstly, UAGA roughly separates known classes from unknown class, by training a graph neural network encoder and a neighborhood-aggregation node classifier in an adversarial framework. Then, unknown-excluded adversarial domain alignment is customized to align only target nodes from known classes with the source, while pushing target nodes from unknown class far away from the source, by assigning positive and negative domain adaptation coefficient to known class nodes and unknown class nodes. Extensive experiments on real-world datasets demonstrate significant outperformance of the proposed UAGA over state-of-the-art methods on O-CNNC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10967v1-abstract-full').style.display = 'none'; document.getElementById('2502.10967v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Xiao Shen, Zhihao Chen, Shirui Pan, Shuang Zhou, Laurence T. Yang, and Xi Zhou. Open-set Cross-network Node Classification via Unknown-excluded Adversarial Graph Domain Alignment. In Proc. AAAI, 2025 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10765">arXiv:2502.10765</a> <span> [<a href="https://arxiv.org/pdf/2502.10765">pdf</a>, <a href="https://arxiv.org/format/2502.10765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Resource Allocation and Pricing for Blockchain-enabled Metaverse: A Stackelberg Game Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhu%2C+Z">Zhanpeng Zhu</a>, <a href="/search/?searchtype=author&query=Lin%2C+F">Feilong Lin</a>, <a href="/search/?searchtype=author&query=Tang%2C+C">Changbing Tang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhongyu 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="2502.10765v1-abstract-short" style="display: inline;"> As the next-generation Internet paradigm, the metaverse can provide users with immersive physical-virtual experiences without spatial limitations. However, there are various concerns to be overcome, such as resource allocation, resource pricing, and transaction security issues. To address the above challenges, we integrate blockchain technology into the metaverse to manage and automate complex int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10765v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10765v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10765v1-abstract-full" style="display: none;"> As the next-generation Internet paradigm, the metaverse can provide users with immersive physical-virtual experiences without spatial limitations. However, there are various concerns to be overcome, such as resource allocation, resource pricing, and transaction security issues. To address the above challenges, we integrate blockchain technology into the metaverse to manage and automate complex interactions effectively and securely utilizing the advantages of blockchain. With the objective of promoting the Quality of Experience (QoE), Metaverse Service Users (MSUs) purchase rendering and bandwidth resources from the Metaverse Service Provider (MSP) to access low-latency and high-quality immersive services. The MSP maximizes the profit by controlling the unit prices of resources. In this paper, we model the interaction between the MSP and MSUs as a Stackelberg game, in which the MSP acts as the leader and MSUs are followers. The existence of Stackelberg equilibrium is analyzed and proved mathematically. Besides, we propose an efficient greedy-and-search-based resource allocation and pricing algorithm (GSRAP) to solve the Stackelberg equilibrium (SE) point. Finally, we conduct extensive simulations to verify the effectiveness and efficiency of our designs. The experiment results show that our algorithm outperforms the baseline scheme in terms of improving the MSP's profit and convergence speed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10765v1-abstract-full').style.display = 'none'; document.getElementById('2502.10765v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10696">arXiv:2502.10696</a> <span> [<a href="https://arxiv.org/pdf/2502.10696">pdf</a>, <a href="https://arxiv.org/format/2502.10696">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"> Improving Retrieval-Augmented Deep Assertion Generation via Joint Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+Q">Quanjun Zhang</a>, <a href="/search/?searchtype=author&query=Fang%2C+C">Chunrong Fang</a>, <a href="/search/?searchtype=author&query=Zheng%2C+Y">Yi Zheng</a>, <a href="/search/?searchtype=author&query=Qian%2C+R">Ruixiang Qian</a>, <a href="/search/?searchtype=author&query=Yu%2C+S">Shengcheng Yu</a>, <a href="/search/?searchtype=author&query=Zhao%2C+Y">Yuan Zhao</a>, <a href="/search/?searchtype=author&query=Zhou%2C+J">Jianyi Zhou</a>, <a href="/search/?searchtype=author&query=Yang%2C+Y">Yun Yang</a>, <a href="/search/?searchtype=author&query=Zheng%2C+T">Tao Zheng</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhenyu 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="2502.10696v1-abstract-short" style="display: inline;"> Unit testing attempts to validate the correctness of basic units of the software system under test and has a crucial role in software development and testing. Very recent work proposes a retrieve-and-edit approach to generate unit test oracles, i.e., assertions. Despite being promising, it is still far from perfect due to some limitations, such as splitting assertion retrieval and generation into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10696v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10696v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10696v1-abstract-full" style="display: none;"> Unit testing attempts to validate the correctness of basic units of the software system under test and has a crucial role in software development and testing. Very recent work proposes a retrieve-and-edit approach to generate unit test oracles, i.e., assertions. Despite being promising, it is still far from perfect due to some limitations, such as splitting assertion retrieval and generation into two separate components without benefiting each other. In this paper, we propose AG-RAG, a retrieval-augmented automated assertion generation approach that leverages external codebases and joint training to address various technical limitations of prior work. Inspired by the plastic surgery hypothesis, AG-RAG attempts to combine relevant unit tests and advanced pre-trained language models (PLMs) with retrieval-augmented fine-tuning. AG-RAG builds a dense retriever to search for relevant test-assert pairs (TAPs) with semantic matching and a retrieval-augmented generator to synthesize accurate assertions with the focal-test and retrieved TAPs as input. Besides, AG-RAG leverages a code-aware language model CodeT5 as the cornerstone to facilitate both assertion retrieval and generation tasks. Furthermore, the retriever is optimized in conjunction with the generator as a whole pipeline with a joint training strategy. This unified design fully adapts both components specifically for retrieving more useful TAPs, thereby generating accurate assertions. We extensively evaluate AG-RAG against six state-of-the-art AG approaches on two benchmarks and three metrics. Experimental results show that AG-RAG significantly outperforms previous AG approaches on all benchmarks and metrics, e.g., improving the most recent baseline EditAS by 20.82% and 26.98% in terms of accuracy. AG-RAG also correctly generates 1739 and 2866 unique assertions that all baselines fail to generate, 3.45X and 9.20X more than EditAS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10696v1-abstract-full').style.display = 'none'; document.getElementById('2502.10696v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 IEEE Transactions on Software Engineering (TSE 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/2502.10438">arXiv:2502.10438</a> <span> [<a href="https://arxiv.org/pdf/2502.10438">pdf</a>, <a href="https://arxiv.org/format/2502.10438">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Injecting Universal Jailbreak Backdoors into LLMs in Minutes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhuowei Chen</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Q">Qiannan Zhang</a>, <a href="/search/?searchtype=author&query=Pei%2C+S">Shichao Pei</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="2502.10438v1-abstract-short" style="display: inline;"> Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this work, we propose JailbreakEdit, a novel jailbreak backdoor injection method that exploits model editing techniques to inject a universal jailbreak backdoor into safety-aligned LLMs… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10438v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10438v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10438v1-abstract-full" style="display: none;"> Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this work, we propose JailbreakEdit, a novel jailbreak backdoor injection method that exploits model editing techniques to inject a universal jailbreak backdoor into safety-aligned LLMs with minimal intervention in minutes. JailbreakEdit integrates a multi-node target estimation to estimate the jailbreak space, thus creating shortcuts from the backdoor to this estimated jailbreak space that induce jailbreak actions. Our attack effectively shifts the models' attention by attaching strong semantics to the backdoor, enabling it to bypass internal safety mechanisms. Experimental results show that JailbreakEdit achieves a high jailbreak success rate on jailbreak prompts while preserving generation quality, and safe performance on normal queries. Our findings underscore the effectiveness, stealthiness, and explainability of JailbreakEdit, emphasizing the need for more advanced defense mechanisms in LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10438v1-abstract-full').style.display = 'none'; document.getElementById('2502.10438v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 ICLR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10291">arXiv:2502.10291</a> <span> [<a href="https://arxiv.org/pdf/2502.10291">pdf</a>, <a href="https://arxiv.org/format/2502.10291">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Angular analysis of $B^0\rightarrow K^{*0}e^{+}e^{-}$ decays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1115 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="2502.10291v1-abstract-short" style="display: inline;"> An angular analysis of $B^0\rightarrow K^{*0}e^{+}e^{-}$ decays is presented using proton-proton collision data collected by the LHCb experiment at centre-of-mass energies of 7, 8 and 13 TeV, corresponding to an integrated luminosity of 9 fb$^{-1}$. The analysis is performed in the region of the dilepton invariant mass squared of 1.1-6.0 GeV$^{2}/c^{4}$. In addition, a test of lepton flavour unive… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10291v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10291v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10291v1-abstract-full" style="display: none;"> An angular analysis of $B^0\rightarrow K^{*0}e^{+}e^{-}$ decays is presented using proton-proton collision data collected by the LHCb experiment at centre-of-mass energies of 7, 8 and 13 TeV, corresponding to an integrated luminosity of 9 fb$^{-1}$. The analysis is performed in the region of the dilepton invariant mass squared of 1.1-6.0 GeV$^{2}/c^{4}$. In addition, a test of lepton flavour universality is performed by comparing the obtained angular observables with those measured in $B^0\rightarrow K^{*0}渭^{+}渭^{-}$ decays. In general, the angular observables are found to be consistent with the Standard Model expectations as well as with global analyses of other $b \rightarrow s \ell^{+} \ell^{-}$ processes, where $\ell$ is either a muon or an electron. No sign of lepton-flavour-violating effects is observed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10291v1-abstract-full').style.display = 'none'; document.getElementById('2502.10291v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/1628/ (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LHCb-PAPER-2024-022, CERN-EP-2025-001 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10019">arXiv:2502.10019</a> <span> [<a href="https://arxiv.org/pdf/2502.10019">pdf</a>, <a href="https://arxiv.org/ps/2502.10019">ps</a>, <a href="https://arxiv.org/format/2502.10019">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> A Differential Equation Approach to the Most-Informative Boolean Function Conjecture </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zijie Chen</a>, <a href="/search/?searchtype=author&query=Gohari%2C+A">Amin Gohari</a>, <a href="/search/?searchtype=author&query=Nair%2C+C">Chandra Nair</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="2502.10019v1-abstract-short" style="display: inline;"> We study the most-informative Boolean function conjecture using a differential equation approach. This leads to a formulation of a functional inequality on finite-dimensional random variables. We also develop a similar inequality in the case of the Hellinger conjecture. Finally, we conjecture a specific finite dimensional inequality that, if proved, will lead to a proof of the Boolean function con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10019v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10019v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10019v1-abstract-full" style="display: none;"> We study the most-informative Boolean function conjecture using a differential equation approach. This leads to a formulation of a functional inequality on finite-dimensional random variables. We also develop a similar inequality in the case of the Hellinger conjecture. Finally, we conjecture a specific finite dimensional inequality that, if proved, will lead to a proof of the Boolean function conjecture in the balanced case. We further show that the above inequality holds modulo four explicit inequalities (all of which seems to hold via numerical simulation) with the first three containing just two variables and a final one involving four variables. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10019v1-abstract-full').style.display = 'none'; document.getElementById('2502.10019v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">17 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/2502.09873">arXiv:2502.09873</a> <span> [<a href="https://arxiv.org/pdf/2502.09873">pdf</a>, <a href="https://arxiv.org/format/2502.09873">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Guo%2C+J">Jinpei Guo</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zheng Chen</a>, <a href="/search/?searchtype=author&query=Li%2C+W">Wenbo Li</a>, <a href="/search/?searchtype=author&query=Guo%2C+Y">Yong Guo</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yulun 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="2502.09873v2-abstract-short" style="display: inline;"> Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especially in highly compressed images. To address these challenges, we propose CODiff, a compression-aware… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09873v2-abstract-full').style.display = 'inline'; document.getElementById('2502.09873v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09873v2-abstract-full" style="display: none;"> Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especially in highly compressed images. To address these challenges, we propose CODiff, a compression-aware one-step diffusion model for JPEG artifact removal. The core of CODiff is the compression-aware visual embedder (CaVE), which extracts and leverages JPEG compression priors to guide the diffusion model. We propose a dual learning strategy that combines explicit and implicit learning. Specifically, explicit learning enforces a quality prediction objective to differentiate low-quality images with different compression levels. Implicit learning employs a reconstruction objective that enhances the model's generalization. This dual learning allows for a deeper and more comprehensive understanding of JPEG compression. Experimental results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics. The code and models will be released at https://github.com/jp-guo/CODiff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09873v2-abstract-full').style.display = 'none'; document.getElementById('2502.09873v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09793">arXiv:2502.09793</a> <span> [<a href="https://arxiv.org/pdf/2502.09793">pdf</a>, <a href="https://arxiv.org/format/2502.09793">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"> Noise Controlled CT Super-Resolution with Conditional Diffusion Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wang%2C+Y">Yuang Wang</a>, <a href="/search/?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/?searchtype=author&query=Hu%2C+R">Rui Hu</a>, <a href="/search/?searchtype=author&query=Yu%2C+B">Baihui Yu</a>, <a href="/search/?searchtype=author&query=Lee%2C+D">Duhgoon Lee</a>, <a href="/search/?searchtype=author&query=Gupta%2C+R">Rajiv Gupta</a>, <a href="/search/?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhiqiang Chen</a>, <a href="/search/?searchtype=author&query=Wu%2C+D">Dufan 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="2502.09793v1-abstract-short" style="display: inline;"> Improving the spatial resolution of CT images is a meaningful yet challenging task, often accompanied by the issue of noise amplification. This article introduces an innovative framework for noise-controlled CT super-resolution utilizing the conditional diffusion model. The model is trained on hybrid datasets, combining noise-matched simulation data with segmented details from real data. Experimen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09793v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09793v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09793v1-abstract-full" style="display: none;"> Improving the spatial resolution of CT images is a meaningful yet challenging task, often accompanied by the issue of noise amplification. This article introduces an innovative framework for noise-controlled CT super-resolution utilizing the conditional diffusion model. The model is trained on hybrid datasets, combining noise-matched simulation data with segmented details from real data. Experimental results with real CT images validate the effectiveness of our proposed framework, showing its potential for practical applications in CT imaging. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09793v1-abstract-full').style.display = 'none'; document.getElementById('2502.09793v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 8th International Conference on Image Formation in X-Ray Computed Tomography, Bamberg, Germany, August 5 - 9, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09454">arXiv:2502.09454</a> <span> [<a href="https://arxiv.org/pdf/2502.09454">pdf</a>, <a href="https://arxiv.org/format/2502.09454">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Search for Heavy Neutral Leptons with IceCube DeepCore </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Abbasi%2C+R">R. Abbasi</a>, <a href="/search/?searchtype=author&query=Ackermann%2C+M">M. Ackermann</a>, <a href="/search/?searchtype=author&query=Adams%2C+J">J. Adams</a>, <a href="/search/?searchtype=author&query=Agarwalla%2C+S+K">S. K. Agarwalla</a>, <a href="/search/?searchtype=author&query=Aguilar%2C+J+A">J. A. Aguilar</a>, <a href="/search/?searchtype=author&query=Ahlers%2C+M">M. Ahlers</a>, <a href="/search/?searchtype=author&query=Alameddine%2C+J+M">J. M. Alameddine</a>, <a href="/search/?searchtype=author&query=Amin%2C+N+M">N. M. Amin</a>, <a href="/search/?searchtype=author&query=Andeen%2C+K">K. Andeen</a>, <a href="/search/?searchtype=author&query=Arg%C3%BCelles%2C+C">C. Arg眉elles</a>, <a href="/search/?searchtype=author&query=Ashida%2C+Y">Y. Ashida</a>, <a href="/search/?searchtype=author&query=Athanasiadou%2C+S">S. Athanasiadou</a>, <a href="/search/?searchtype=author&query=Axani%2C+S+N">S. N. Axani</a>, <a href="/search/?searchtype=author&query=Babu%2C+R">R. Babu</a>, <a href="/search/?searchtype=author&query=Bai%2C+X">X. Bai</a>, <a href="/search/?searchtype=author&query=V.%2C+A+B">A. Balagopal V.</a>, <a href="/search/?searchtype=author&query=Baricevic%2C+M">M. Baricevic</a>, <a href="/search/?searchtype=author&query=Barwick%2C+S+W">S. W. Barwick</a>, <a href="/search/?searchtype=author&query=Bash%2C+S">S. Bash</a>, <a href="/search/?searchtype=author&query=Basu%2C+V">V. Basu</a>, <a href="/search/?searchtype=author&query=Bay%2C+R">R. Bay</a>, <a href="/search/?searchtype=author&query=Beatty%2C+J+J">J. J. Beatty</a>, <a href="/search/?searchtype=author&query=Tjus%2C+J+B">J. Becker Tjus</a>, <a href="/search/?searchtype=author&query=Beise%2C+J">J. Beise</a>, <a href="/search/?searchtype=author&query=Bellenghi%2C+C">C. Bellenghi</a> , et al. (400 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="2502.09454v1-abstract-short" style="display: inline;"> The observation of neutrino oscillations has established that neutrinos have non-zero masses. This phenomenon is not explained by the Standard Model of particle physics, but one viable explanation to this dilemma involves the existence of heavy neutral leptons in the form of right-handed neutrinos. This work presents the first search for heavy neutral leptons with the IceCube Neutrino Observatory.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09454v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09454v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09454v1-abstract-full" style="display: none;"> The observation of neutrino oscillations has established that neutrinos have non-zero masses. This phenomenon is not explained by the Standard Model of particle physics, but one viable explanation to this dilemma involves the existence of heavy neutral leptons in the form of right-handed neutrinos. This work presents the first search for heavy neutral leptons with the IceCube Neutrino Observatory. The standard three flavor neutrino model is extended by adding a fourth GeV-scale mass state allowing mixing with the $蟿$ sector through the parameter $|U_{\tau4}|^2$. The analysis is performed by searching for signatures of heavy neutral leptons that are directly produced via up-scattering of atmospheric $谓_蟿$'s inside the IceCube detection volume. Three heavy neutral lepton mass values, $m_4$, of 0.3 GeV, 0.6 GeV, and 1.0 GeV are tested using ten years of data, collected between 2011 and 2021. No significant signal of heavy neutral leptons is observed for any of the tested masses. The resulting constraints for the mixing parameter are $|U_{\tau4}|^2 < 0.19$ ($m_4 = 0.3$ GeV), $|U_{\tau4}|^2 < 0.36$ ($m_4 = 0.6$ GeV), and $|U_{\tau4}|^2 < 0.40$ ($m_4 = 1.0$ GeV) at the 90% confidence level. This analysis serves as proof-of-concept for heavy neutral lepton searches in IceCube. The heavy neutral lepton event generator, developed in this work, and the analysis of the expected signatures lay the fundamental groundwork for future searches thereof. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09454v1-abstract-full').style.display = 'none'; document.getElementById('2502.09454v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09423">arXiv:2502.09423</a> <span> [<a href="https://arxiv.org/pdf/2502.09423">pdf</a>, <a href="https://arxiv.org/format/2502.09423">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</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"> Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Ziyi Chen</a>, <a href="/search/?searchtype=author&query=Yuan%2C+Y">Yang Yuan</a>, <a href="/search/?searchtype=author&query=Zheng%2C+S">Siming Zheng</a>, <a href="/search/?searchtype=author&query=Guo%2C+J">Jialong Guo</a>, <a href="/search/?searchtype=author&query=Liang%2C+S">Sihan Liang</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yangang Wang</a>, <a href="/search/?searchtype=author&query=Wang%2C+Z">Zongguo 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="2502.09423v1-abstract-short" style="display: inline;"> Crystal structure forms the foundation for understanding the physical and chemical properties of materials. Generative models have emerged as a new paradigm in crystal structure prediction(CSP), however, accurately capturing key characteristics of crystal structures, such as periodicity and symmetry, remains a significant challenge. In this paper, we propose a Transformer-Enhanced Variational Auto… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09423v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09423v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09423v1-abstract-full" style="display: none;"> Crystal structure forms the foundation for understanding the physical and chemical properties of materials. Generative models have emerged as a new paradigm in crystal structure prediction(CSP), however, accurately capturing key characteristics of crystal structures, such as periodicity and symmetry, remains a significant challenge. In this paper, we propose a Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction (TransVAE-CSP), who learns the characteristic distribution space of stable materials, enabling both the reconstruction and generation of crystal structures. TransVAE-CSP integrates adaptive distance expansion with irreducible representation to effectively capture the periodicity and symmetry of crystal structures, and the encoder is a transformer network based on an equivariant dot product attention mechanism. Experimental results on the carbon_24, perov_5, and mp_20 datasets demonstrate that TransVAE-CSP outperforms existing methods in structure reconstruction and generation tasks under various modeling metrics, offering a powerful tool for crystal structure design and optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09423v1-abstract-full').style.display = 'none'; document.getElementById('2502.09423v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09101">arXiv:2502.09101</a> <span> [<a href="https://arxiv.org/pdf/2502.09101">pdf</a>, <a href="https://arxiv.org/format/2502.09101">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Bridging the Gap Between LLMs and Human Intentions: Progresses and Challenges in Instruction Understanding, Intention Reasoning, and Reliable Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chang%2C+Z">Zongyu Chang</a>, <a href="/search/?searchtype=author&query=Lu%2C+F">Feihong Lu</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Z">Ziqin Zhu</a>, <a href="/search/?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/?searchtype=author&query=Ji%2C+C">Cheng Ji</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/?searchtype=author&query=Xu%2C+R">Ruifeng Xu</a>, <a href="/search/?searchtype=author&query=Song%2C+Y">Yangqiu Song</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Shangguang Wang</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jianxin 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="2502.09101v1-abstract-short" style="display: inline;"> Large language models (LLMs) have demonstrated exceptional capabilities in understanding and generation. However, when interacting with human instructions in real-world scenarios, LLMs still face significant challenges, particularly in accurately capturing and comprehending human instructions and intentions. This paper focuses on three challenges in LLM-based text generation tasks: instruction und… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09101v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09101v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09101v1-abstract-full" style="display: none;"> Large language models (LLMs) have demonstrated exceptional capabilities in understanding and generation. However, when interacting with human instructions in real-world scenarios, LLMs still face significant challenges, particularly in accurately capturing and comprehending human instructions and intentions. This paper focuses on three challenges in LLM-based text generation tasks: instruction understanding, intention reasoning, and reliable generation. Regarding human complex instruction, LLMs have deficiencies in understanding long contexts and instructions in multi-round conversations. For intention reasoning, LLMs may have inconsistent command reasoning, difficulty reasoning about commands containing incorrect information, difficulty understanding user ambiguous language commands, and a weak understanding of user intention in commands. Besides, In terms of reliable generation, LLMs may have unstable generated content and unethical generation. To this end, we classify and analyze the performance of LLMs in challenging scenarios and conduct a comprehensive evaluation of existing solutions. Furthermore, we introduce benchmarks and categorize them based on the aforementioned three core challenges. Finally, we explore potential directions for future research to enhance the reliability and adaptability of LLMs in real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09101v1-abstract-full').style.display = 'none'; document.getElementById('2502.09101v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">9 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09093">arXiv:2502.09093</a> <span> [<a href="https://arxiv.org/pdf/2502.09093">pdf</a>, <a href="https://arxiv.org/format/2502.09093">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"> From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Li%2C+M">Mingxiao Li</a>, <a href="/search/?searchtype=author&query=Qu%2C+F">Fang Qu</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhanpeng Chen</a>, <a href="/search/?searchtype=author&query=Su%2C+N">Na Su</a>, <a href="/search/?searchtype=author&query=Zhong%2C+Z">Zhizhou Zhong</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Ziyang Chen</a>, <a href="/search/?searchtype=author&query=Du%2C+N">Nan Du</a>, <a href="/search/?searchtype=author&query=Li%2C+X">Xiaolong 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="2502.09093v1-abstract-short" style="display: inline;"> While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09093v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09093v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09093v1-abstract-full" style="display: none;"> While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into autoregressive training. Existing MLLMs primarily focused on recovering information from textual inputs, often neglecting the effective processing of image data. In contrast, the key improvement of this work is the reinterpretation of multimodal alignment as a process of recovering information from input data, with particular emphasis on reconstructing detailed visual features.The proposed method seamlessly integrates into standard models without architectural changes. Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09093v1-abstract-full').style.display = 'none'; document.getElementById('2502.09093v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09064">arXiv:2502.09064</a> <span> [<a href="https://arxiv.org/pdf/2502.09064">pdf</a>, <a href="https://arxiv.org/format/2502.09064">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"> StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zichong Chen</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Shijin Wang</a>, <a href="/search/?searchtype=author&query=Zhou%2C+Y">Yang 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="2502.09064v1-abstract-short" style="display: inline;"> Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to learn and apply style representations from a limited set of reference images, enabling content synthesis of both text-aligned and stylistically coherent. Our appro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09064v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09064v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09064v1-abstract-full" style="display: none;"> Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to learn and apply style representations from a limited set of reference images, enabling content synthesis of both text-aligned and stylistically coherent. Our approach uniquely decomposes style into two components, composition and texture, each learned through different strategies. We then leverage two synthesis branches, each focusing on a corresponding style component, to facilitate effective style blending through shared features without affecting content generation. StyleBlend addresses the common issues of text misalignment and weak style representation that previous methods have struggled with. Extensive qualitative and quantitative comparisons demonstrate the superiority of our approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09064v1-abstract-full').style.display = 'none'; document.getElementById('2502.09064v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 Eurographics 2025. Project page: https://zichongc.github.io/StyleBlend/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.08929">arXiv:2502.08929</a> <span> [<a href="https://arxiv.org/pdf/2502.08929">pdf</a>, <a href="https://arxiv.org/ps/2502.08929">ps</a>, <a href="https://arxiv.org/format/2502.08929">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Precise Measurement of the $蠂_{c0}$ Resonance Parameters and Branching Fractions of $蠂_{c0,c2}\to蟺^+蟺^-/K^+K^-$ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=BESIII+Collaboration"> BESIII Collaboration</a>, <a href="/search/?searchtype=author&query=Ablikim%2C+M">M. Ablikim</a>, <a href="/search/?searchtype=author&query=Achasov%2C+M+N">M. N. Achasov</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Afedulidis%2C+O">O. Afedulidis</a>, <a href="/search/?searchtype=author&query=Ai%2C+X+C">X. C. Ai</a>, <a href="/search/?searchtype=author&query=Aliberti%2C+R">R. Aliberti</a>, <a href="/search/?searchtype=author&query=Amoroso%2C+A">A. Amoroso</a>, <a href="/search/?searchtype=author&query=Bai%2C+Y">Y. Bai</a>, <a href="/search/?searchtype=author&query=Bakina%2C+O">O. Bakina</a>, <a href="/search/?searchtype=author&query=Balossino%2C+I">I. Balossino</a>, <a href="/search/?searchtype=author&query=Ban%2C+Y">Y. Ban</a>, <a href="/search/?searchtype=author&query=Bao%2C+H+-">H. -R. Bao</a>, <a href="/search/?searchtype=author&query=Batozskaya%2C+V">V. Batozskaya</a>, <a href="/search/?searchtype=author&query=Begzsuren%2C+K">K. Begzsuren</a>, <a href="/search/?searchtype=author&query=Berger%2C+N">N. Berger</a>, <a href="/search/?searchtype=author&query=Berlowski%2C+M">M. Berlowski</a>, <a href="/search/?searchtype=author&query=Bertani%2C+M">M. Bertani</a>, <a href="/search/?searchtype=author&query=Bettoni%2C+D">D. Bettoni</a>, <a href="/search/?searchtype=author&query=Bianchi%2C+F">F. Bianchi</a>, <a href="/search/?searchtype=author&query=Bianco%2C+E">E. Bianco</a>, <a href="/search/?searchtype=author&query=Bortone%2C+A">A. Bortone</a>, <a href="/search/?searchtype=author&query=Boyko%2C+I">I. Boyko</a>, <a href="/search/?searchtype=author&query=Briere%2C+R+A">R. A. Briere</a>, <a href="/search/?searchtype=author&query=Brueggemann%2C+A">A. Brueggemann</a> , et al. (648 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="2502.08929v1-abstract-short" style="display: inline;"> By analyzing a $蠄(3686)$ data sample containing $(107.7\pm0.6)\times10^{6}$ events taken with the BESIII detector at the BEPCII storage ring in 2009, the $蠂_{c0}$ resonance parameters are precisely measured using $蠂_{c0,c2} \to 蟺^+蟺^-/K^+K^-$ events. The mass of $蠂_{c0}$ is determined to be $M(蠂_{c0})=(3415.67\pm0.07\pm0.06\pm0.07$)~MeV/$c^2$, and its full width is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08929v1-abstract-full').style.display = 'inline'; document.getElementById('2502.08929v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08929v1-abstract-full" style="display: none;"> By analyzing a $蠄(3686)$ data sample containing $(107.7\pm0.6)\times10^{6}$ events taken with the BESIII detector at the BEPCII storage ring in 2009, the $蠂_{c0}$ resonance parameters are precisely measured using $蠂_{c0,c2} \to 蟺^+蟺^-/K^+K^-$ events. The mass of $蠂_{c0}$ is determined to be $M(蠂_{c0})=(3415.67\pm0.07\pm0.06\pm0.07$)~MeV/$c^2$, and its full width is $螕(蠂_{c0})=(12.44\pm0.12\pm0.12)~{\rm MeV}$, where the first uncertainty is statistical, the second systematic, and the third for mass comes from $蠂_{c2}$ mass uncertainty. These measurements improve the precision of $蠂_{c0}$ mass by a factor of four and width by one order of magnitude over the previous individual measurements, and significantly boost our knowledge about the charmonium spectrum. Together with additional $(345.4\pm2.6)\times10^{6}$ $蠄(3686)$ data events taken in 2012, the decay branching fractions of $蠂_{c0,c2}\to蟺^+蟺^-/K^+K^-$ are measured as well, with precision improved by a factor of three compared to previous measurements. These $蠂_{c0}$ decay branching fractions provide important inputs for the study of glueballs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08929v1-abstract-full').style.display = 'none'; document.getElementById('2502.08929v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">9 pages, 1 figure</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Chen%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository