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 380 results for author: <span class="mathjax">Luo, S</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Luo%2C+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Luo, S"> </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=Luo%2C+S&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="Luo, S"> <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=Luo%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20430">arXiv:2503.20430</a> <span> [<a href="https://arxiv.org/pdf/2503.20430">pdf</a>, <a href="https://arxiv.org/format/2503.20430">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sichun Luo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jian Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaojie Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Linrong Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sicong Liu</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+H">Hanxu Hou</a>, <a href="/search/cs?searchtype=author&query=Song%2C+L">Linqi Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20430v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items and improve system performance. However, existing RAG methods have two shortcomings. \textit{(i)} In the \textit{retrieval} stage, they rely primarily on textu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20430v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20430v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20430v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items and improve system performance. However, existing RAG methods have two shortcomings. \textit{(i)} In the \textit{retrieval} stage, they rely primarily on textual semantics and often fail to incorporate the most relevant items, thus constraining system effectiveness. \textit{(ii)} In the \textit{generation} stage, they lack explicit chain-of-thought reasoning, further limiting their potential. In this paper, we propose Representation learning and \textbf{R}easoning empowered retrieval-\textbf{A}ugmented \textbf{L}arge \textbf{L}anguage model \textbf{Rec}ommendation (RALLRec+). Specifically, for the retrieval stage, we prompt LLMs to generate detailed item descriptions and perform joint representation learning, combining textual and collaborative signals extracted from the LLM and recommendation models, respectively. To account for the time-varying nature of user interests, we propose a simple yet effective reranking method to capture preference dynamics. For the generation phase, we first evaluate reasoning LLMs on recommendation tasks, uncovering valuable insights. Then we introduce knowledge-injected prompting and consistency-based merging approach to integrate reasoning LLMs with general-purpose LLMs, enhancing overall performance. Extensive experiments on three real world datasets validate our method's effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20430v1-abstract-full').style.display = 'none'; document.getElementById('2503.20430v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2502.06101</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.20299">arXiv:2503.20299</a> <span> [<a href="https://arxiv.org/pdf/2503.20299">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> Finding Near-Optimal Maximum Set of Disjoint $k$-Cliques in Real-World Social Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+W">Wenqing Lin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xin Chen</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+H">Haoxuan Xie</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sibo Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siqiang Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.20299v1-abstract-short" style="display: inline;"> A $k$-clique is a dense graph, consisting of $k$ fully-connected nodes, that finds numerous applications, such as community detection and network analysis. In this paper, we study a new problem, that finds a maximum set of disjoint $k$-cliques in a given large real-world graph with a user-defined fixed number $k$, which can contribute to a good performance of teaming collaborative events in online… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20299v1-abstract-full').style.display = 'inline'; document.getElementById('2503.20299v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.20299v1-abstract-full" style="display: none;"> A $k$-clique is a dense graph, consisting of $k$ fully-connected nodes, that finds numerous applications, such as community detection and network analysis. In this paper, we study a new problem, that finds a maximum set of disjoint $k$-cliques in a given large real-world graph with a user-defined fixed number $k$, which can contribute to a good performance of teaming collaborative events in online games. However, this problem is NP-hard when $k \geq 3$, making it difficult to solve. To address that, we propose an efficient lightweight method that avoids significant overheads and achieves a $k$-approximation to the optimal, which is equipped with several optimization techniques, including the ordering method, degree estimation in the clique graph, and a lightweight implementation. Besides, to handle dynamic graphs that are widely seen in real-world social networks, we devise an efficient indexing method with careful swapping operations, leading to the efficient maintenance of a near-optimal result with frequent updates in the graph. In various experiments on several large graphs, our proposed approaches significantly outperform the competitors by up to 2 orders of magnitude in running time and 13.3\% in the number of computed disjoint $k$-cliques, which demonstrates the superiority of the proposed approaches in terms of efficiency and effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.20299v1-abstract-full').style.display = 'none'; document.getElementById('2503.20299v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in ICDE 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.18491">arXiv:2503.18491</a> <span> [<a href="https://arxiv.org/pdf/2503.18491">pdf</a>, <a href="https://arxiv.org/format/2503.18491">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"> MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shuo Yang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siwen Luo</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S+C">Soyeon Caren Han</a>, <a href="/search/cs?searchtype=author&query=Hovy%2C+E">Eduard Hovy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.18491v1-abstract-short" style="display: inline;"> Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18491v1-abstract-full').style.display = 'inline'; document.getElementById('2503.18491v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.18491v1-abstract-full" style="display: none;"> Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage process: (1) Explicit Knowledge Integration from external sources, (2) By-Type Post-Processing for contextual refinement, and (3) Implicit Knowledge Augmentation using a Graph Neural Network (GNN) for structured reasoning. While GNNs bring greater depth to structured inference, they enable superior relational inference beyond LVLMs. MAGIC-VQA bridges a key gap by unifying commonsensse knowledge with LVLM-driven reasoning, eliminating the need for extensive pre-training or complex prompt tuning. Our framework achieves state-of-the-art performance on benchmark datasets, significantly improving commonsense reasoning in VQA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.18491v1-abstract-full').style.display = 'none'; document.getElementById('2503.18491v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 Pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17793">arXiv:2503.17793</a> <span> [<a href="https://arxiv.org/pdf/2503.17793">pdf</a>, <a href="https://arxiv.org/format/2503.17793">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Codefuse"> Codefuse</a>, <a href="/search/cs?searchtype=author&query=Team%2C+L">Ling Team</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+W">Wenting Cai</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuchen Cao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chaoyu Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Siba Chen</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Q">Qing Cui</a>, <a href="/search/cs?searchtype=author&query=Di%2C+P">Peng Di</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+J">Junpeng Fang</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+Z">Zi Gong</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+T">Ting Guo</a>, <a href="/search/cs?searchtype=author&query=He%2C+Z">Zhengyu He</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yang Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Cong Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jianguo Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zheng Li</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+S">Shijie Lian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">BingChang Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Songshan Luo</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+S">Shuo Mao</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+M">Min Shen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jian Wu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiaolong Yang</a> , et al. (8 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.17793v1-abstract-short" style="display: inline;"> Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the Deep… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17793v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17793v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17793v1-abstract-full" style="display: none;"> Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{https://huggingface.co/inclusionAI/Ling-Coder-lite}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17793v1-abstract-full').style.display = 'none'; document.getElementById('2503.17793v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.16988">arXiv:2503.16988</a> <span> [<a href="https://arxiv.org/pdf/2503.16988">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> High Accuracy Pulmonary Vessel Segmentation for Contrast and Non-contrast CT Images and Its Clinical Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ming%2C+Y">Ying Ming</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shaoze Luo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+L">Longfei Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Q">Qiqi Xu</a>, <a href="/search/cs?searchtype=author&query=Song%2C+W">Wei Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.16988v1-abstract-short" style="display: inline;"> Accurate segmentation of pulmonary vessels plays a very critical role in diagnosing and assessing various lung diseases. In clinical practice, diagnosis is typically carried out using CTPA images. However, there is a lack of high-precision pulmonary vessel segmentation algorithms for CTPA, and pulmonary vessel segmentation for NCCT poses an even greater challenge. In this study, we propose a 3D im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16988v1-abstract-full').style.display = 'inline'; document.getElementById('2503.16988v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.16988v1-abstract-full" style="display: none;"> Accurate segmentation of pulmonary vessels plays a very critical role in diagnosing and assessing various lung diseases. In clinical practice, diagnosis is typically carried out using CTPA images. However, there is a lack of high-precision pulmonary vessel segmentation algorithms for CTPA, and pulmonary vessel segmentation for NCCT poses an even greater challenge. In this study, we propose a 3D image segmentation algorithm for automated pulmonary vessel segmentation from both contrast and non-contrast CT images. In the network, we designed a Vessel Lumen Structure Optimization Module (VLSOM), which extracts the centerline of vessels and adjusts the weights based on the positional information and adds a Cl-Dice-Loss to supervise the stability of the vessels structure. In addition, we designed a method for generating vessel GT from CTPA to NCCT for training models that support both CTPA and NCCT. In this work, we used 427 sets of high-precision annotated CT data from multiple vendors and countries. Finally, our experimental model achieved Cl-Recall, Cl-DICE and Recall values of 0.879, 0.909, 0.934 (CTPA) and 0.928, 0.936, 0.955 (NCCT) respectively. This shows that our model has achieved good performance in both accuracy and completeness of pulmonary vessel segmentation. In clinical visual evaluation, our model also had good segmentation performance on various disease types and can assist doctors in medical diagnosis, verifying the great potential of this method in clinical application. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.16988v1-abstract-full').style.display = 'none'; document.getElementById('2503.16988v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15078">arXiv:2503.15078</a> <span> [<a href="https://arxiv.org/pdf/2503.15078">pdf</a>, <a href="https://arxiv.org/ps/2503.15078">ps</a>, <a href="https://arxiv.org/format/2503.15078">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> </div> </div> <p class="title is-5 mathjax"> Fast But Accurate: A Real-Time Hyperelastic Simulator with Robust Frictional Contact </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+Z">Ziqiu Zeng</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siyuan Luo</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+F">Fan Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhongkai Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.15078v1-abstract-short" style="display: inline;"> We present a GPU-friendly framework for real-time implicit simulation of elastic material in the presence of frictional contacts. The integration of hyperelasticity, non-interpenetration contact, and friction in real-time simulations presents formidable nonlinear and non-smooth problems, which are highly challenging to solve. By incorporating nonlinear complementarity conditions within the local-g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15078v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15078v1-abstract-full" style="display: none;"> We present a GPU-friendly framework for real-time implicit simulation of elastic material in the presence of frictional contacts. The integration of hyperelasticity, non-interpenetration contact, and friction in real-time simulations presents formidable nonlinear and non-smooth problems, which are highly challenging to solve. By incorporating nonlinear complementarity conditions within the local-global framework, we achieve rapid convergence in addressing these challenges. While the structure of local-global methods is not fully GPU-friendly, our proposal of a simple yet efficient solver with sparse presentation of the system inverse enables highly parallel computing while maintaining a fast convergence rate. Moreover, our novel splitting strategy for non-smooth indicators not only amplifies overall performance but also refines the complementarity preconditioner, enhancing the accuracy of frictional behavior modeling. Through extensive experimentation, the robustness of our framework in managing real-time contact scenarios, ranging from large-scale systems and extreme deformations to non-smooth contacts and precise friction interactions, has been validated. Compatible with a wide range of hyperelastic models, our approach maintains efficiency across both low and high stiffness materials. Despite its remarkable efficiency, robustness, and generality, our method is elegantly simple, with its core contributions grounded solely on standard matrix operations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15078v1-abstract-full').style.display = 'none'; document.getElementById('2503.15078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.14945">arXiv:2503.14945</a> <span> [<a href="https://arxiv.org/pdf/2503.14945">pdf</a>, <a href="https://arxiv.org/format/2503.14945">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Generating Multimodal Driving Scenes via Next-Scene Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanhao Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haoyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Tianwei Lin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+L">Lichao Huang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shujie Luo</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+R">Rui Wu</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+C">Congpei Qiu</a>, <a href="/search/cs?searchtype=author&query=Ke%2C+W">Wei Ke</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tong Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.14945v2-abstract-short" style="display: inline;"> Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14945v2-abstract-full').style.display = 'inline'; document.getElementById('2503.14945v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.14945v2-abstract-full" style="display: none;"> Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of map modality. With tokenized modalities, our scene sequence generation framework autoregressively predicts each scene while managing computational demands through a two-stage approach. The Temporal AutoRegressive (TAR) component captures inter-frame dynamics for each modality while the Ordered AutoRegressive (OAR) component aligns modalities within each scene by sequentially predicting tokens in a fixed order. To maintain coherence between map and ego-action modalities, we introduce the Action-aware Map Alignment (AMA) module, which applies a transformation based on the ego-action to maintain coherence between these modalities. Our framework effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements. Project page: https://yanhaowu.github.io/UMGen/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.14945v2-abstract-full').style.display = 'none'; document.getElementById('2503.14945v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.12014">arXiv:2503.12014</a> <span> [<a href="https://arxiv.org/pdf/2503.12014">pdf</a>, <a href="https://arxiv.org/format/2503.12014">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Learning Dual-Domain Multi-Scale Representations for Single Image Deraining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zou%2C+S">Shun Zou</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yi Zou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mingya Zhang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shipeng Luo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+G">Guangwei Gao</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+G">Guojun Qi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.12014v1-abstract-short" style="display: inline;"> Existing image deraining methods typically rely on single-input, single-output, and single-scale architectures, which overlook the joint multi-scale information between external and internal features. Furthermore, single-domain representations are often too restrictive, limiting their ability to handle the complexities of real-world rain scenarios. To address these challenges, we propose a novel D… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12014v1-abstract-full').style.display = 'inline'; document.getElementById('2503.12014v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.12014v1-abstract-full" style="display: none;"> Existing image deraining methods typically rely on single-input, single-output, and single-scale architectures, which overlook the joint multi-scale information between external and internal features. Furthermore, single-domain representations are often too restrictive, limiting their ability to handle the complexities of real-world rain scenarios. To address these challenges, we propose a novel Dual-Domain Multi-Scale Representation Network (DMSR). The key idea is to exploit joint multi-scale representations from both external and internal domains in parallel while leveraging the strengths of both spatial and frequency domains to capture more comprehensive properties. Specifically, our method consists of two main components: the Multi-Scale Progressive Spatial Refinement Module (MPSRM) and the Frequency Domain Scale Mixer (FDSM). The MPSRM enables the interaction and coupling of multi-scale expert information within the internal domain using a hierarchical modulation and fusion strategy. The FDSM extracts multi-scale local information in the spatial domain, while also modeling global dependencies in the frequency domain. Extensive experiments show that our model achieves state-of-the-art performance across six benchmark datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.12014v1-abstract-full').style.display = 'none'; document.getElementById('2503.12014v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 5 figures, code: https://zs1314.github.io/DMSR</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.11995">arXiv:2503.11995</a> <span> [<a href="https://arxiv.org/pdf/2503.11995">pdf</a>, <a href="https://arxiv.org/format/2503.11995">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"> Fraesormer: Learning Adaptive Sparse Transformer for Efficient Food Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zou%2C+S">Shun Zou</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yi Zou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mingya Zhang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shipeng Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhihao Chen</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+G">Guangwei Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.11995v1-abstract-short" style="display: inline;"> In recent years, Transformer has witnessed significant progress in food recognition. However, most existing approaches still face two critical challenges in lightweight food recognition: (1) the quadratic complexity and redundant feature representation from interactions with irrelevant tokens; (2) static feature recognition and single-scale representation, which overlook the unstructured, non-fixe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11995v1-abstract-full').style.display = 'inline'; document.getElementById('2503.11995v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.11995v1-abstract-full" style="display: none;"> In recent years, Transformer has witnessed significant progress in food recognition. However, most existing approaches still face two critical challenges in lightweight food recognition: (1) the quadratic complexity and redundant feature representation from interactions with irrelevant tokens; (2) static feature recognition and single-scale representation, which overlook the unstructured, non-fixed nature of food images and the need for multi-scale features. To address these, we propose an adaptive and efficient sparse Transformer architecture (Fraesormer) with two core designs: Adaptive Top-k Sparse Partial Attention (ATK-SPA) and Hierarchical Scale-Sensitive Feature Gating Network (HSSFGN). ATK-SPA uses a learnable Gated Dynamic Top-K Operator (GDTKO) to retain critical attention scores, filtering low query-key matches that hinder feature aggregation. It also introduces a partial channel mechanism to reduce redundancy and promote expert information flow, enabling local-global collaborative modeling. HSSFGN employs gating mechanism to achieve multi-scale feature representation, enhancing contextual semantic information. Extensive experiments show that Fraesormer outperforms state-of-the-art methods. code is available at https://zs1314.github.io/Fraesormer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.11995v1-abstract-full').style.display = 'none'; document.getElementById('2503.11995v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.08005">arXiv:2503.08005</a> <span> [<a href="https://arxiv.org/pdf/2503.08005">pdf</a>, <a href="https://arxiv.org/format/2503.08005">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"> CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhiyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Song%2C+X">Xibin Song</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Senbo Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weizhe Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiayu Yang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Z">Ziang Cheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shenzhou Chen</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+T">Taizhang Shang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Weixuan Sun</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a>, <a href="/search/cs?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="2503.08005v2-abstract-short" style="display: inline;"> 3D object reconstruction from single-view image is a fundamental task in computer vision with wide-ranging applications. Recent advancements in Large Reconstruction Models (LRMs) have shown great promise in leveraging multi-view images generated by 2D diffusion models to extract 3D content. However, challenges remain as 2D diffusion models often struggle to produce dense images with strong multi-v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08005v2-abstract-full').style.display = 'inline'; document.getElementById('2503.08005v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.08005v2-abstract-full" style="display: none;"> 3D object reconstruction from single-view image is a fundamental task in computer vision with wide-ranging applications. Recent advancements in Large Reconstruction Models (LRMs) have shown great promise in leveraging multi-view images generated by 2D diffusion models to extract 3D content. However, challenges remain as 2D diffusion models often struggle to produce dense images with strong multi-view consistency, and LRMs tend to amplify these inconsistencies during the 3D reconstruction process. Addressing these issues is critical for achieving high-quality and efficient 3D reconstruction. In this paper, we present CDI3D, a feed-forward framework designed for efficient, high-quality image-to-3D generation with view interpolation. To tackle the aforementioned challenges, we propose to integrate 2D diffusion-based view interpolation into the LRM pipeline to enhance the quality and consistency of the generated mesh. Specifically, our approach introduces a Dense View Interpolation (DVI) module, which synthesizes interpolated images between main views generated by the 2D diffusion model, effectively densifying the input views with better multi-view consistency. We also design a tilt camera pose trajectory to capture views with different elevations and perspectives. Subsequently, we employ a tri-plane-based mesh reconstruction strategy to extract robust tokens from these interpolated and original views, enabling the generation of high-quality 3D meshes with superior texture and geometry. Extensive experiments demonstrate that our method significantly outperforms previous state-of-the-art approaches across various benchmarks, producing 3D content with enhanced texture fidelity and geometric accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.08005v2-abstract-full').style.display = 'none'; document.getElementById('2503.08005v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.07035">arXiv:2503.07035</a> <span> [<a href="https://arxiv.org/pdf/2503.07035">pdf</a>, <a href="https://arxiv.org/format/2503.07035">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"> Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sheng Luo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yi Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+T">Tao Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.07035v1-abstract-short" style="display: inline;"> Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e. Class IL, Domain IL), or increase by a static scale in a class- and domain-agnostic manner (i.e. Versatile IL (VIL)), which greatly limit their applicability in t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07035v1-abstract-full').style.display = 'inline'; document.getElementById('2503.07035v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.07035v1-abstract-full" style="display: none;"> Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e. Class IL, Domain IL), or increase by a static scale in a class- and domain-agnostic manner (i.e. Versatile IL (VIL)), which greatly limit their applicability in the unpredictable and dynamic wild. In this work, we investigate $\textbf{Universal Incremental Learning (UIL)}$, where a model neither knows which new classes or domains will increase along sequential tasks, nor the scale of the increments within each task. This uncertainty prevents the model from confidently learning knowledge from all task distributions and symmetrically focusing on the diverse knowledge within each task distribution. Consequently, UIL presents a more general and realistic IL scenario, making the model face confusion arising from inter-task and intra-task distribution randomness. To $\textbf{Mi}$tigate both $\textbf{Co}$nfusion, we propose a simple yet effective framework for UIL, named $\textbf{MiCo}$. At the inter-task distribution level, we employ a multi-objective learning scheme to enforce accurate and deterministic predictions, and its effectiveness is further enhanced by a direction recalibration module that reduces conflicting gradients. Moreover, at the intra-task distribution level, we introduce a magnitude recalibration module to alleviate asymmetrical optimization towards imbalanced class distribution. Extensive experiments on three benchmarks demonstrate the effectiveness of our method, outperforming existing state-of-the-art methods in both the UIL scenario and the VIL scenario. Our code will be available at $\href{https://github.com/rolsheng/UIL}{here}$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.07035v1-abstract-full').style.display = 'none'; document.getElementById('2503.07035v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 4 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.04183">arXiv:2503.04183</a> <span> [<a href="https://arxiv.org/pdf/2503.04183">pdf</a>, <a href="https://arxiv.org/format/2503.04183">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"> CrowdHMTware: A Cross-level Co-adaptation Middleware for Context-aware Mobile DL Deployment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+S">Sicong Liu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shiyan Luo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuzhan Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+H">Hao Luo</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yuan Xu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+K">Ke Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yao Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiwen Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.04183v1-abstract-short" style="display: inline;"> There are many deep learning (DL) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives.To enable robust and private mobile sensing, DL models are often deployed locally on resource-constrained mobile devices using techniques such as model compression or offloading.However, existing methods, either front… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04183v1-abstract-full').style.display = 'inline'; document.getElementById('2503.04183v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.04183v1-abstract-full" style="display: none;"> There are many deep learning (DL) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives.To enable robust and private mobile sensing, DL models are often deployed locally on resource-constrained mobile devices using techniques such as model compression or offloading.However, existing methods, either front-end algorithm level (i.e. DL model compression/partitioning) or back-end scheduling level (i.e. operator/resource scheduling), cannot be locally online because they require offline retraining to ensure accuracy or rely on manually pre-defined strategies, struggle with dynamic adaptability.The primary challenge lies in feeding back runtime performance from the back-end level to the front-end level optimization decision. Moreover, the adaptive mobile DL model porting middleware with cross-level co-adaptation is less explored, particularly in mobile environments with diversity and dynamics. In response, we introduce CrowdHMTware, a dynamic context-adaptive DL model deployment middleware for heterogeneous mobile devices. It establishes an automated adaptation loop between cross-level functional components, i.e. elastic inference, scalable offloading, and model-adaptive engine, enhancing scalability and adaptability. Experiments with four typical tasks across 15 platforms and a real-world case study demonstrate that CrowdHMTware can effectively scale DL model, offloading, and engine actions across diverse platforms and tasks. It hides run-time system issues from developers, reducing the required developer expertise. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.04183v1-abstract-full').style.display = 'none'; document.getElementById('2503.04183v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted by IEEE Transactions on Mobile Computing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.02167">arXiv:2503.02167</a> <span> [<a href="https://arxiv.org/pdf/2503.02167">pdf</a>, <a href="https://arxiv.org/format/2503.02167">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Leveraging Large Language Models for Enhanced Digital Twin Modeling: Trends, Methods, and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+L">Linyao Yang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shi Luo</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xi Cheng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Lei Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.02167v1-abstract-short" style="display: inline;"> Digital twin technology is a transformative innovation driving the digital transformation and intelligent optimization of manufacturing systems. By integrating real-time data with computational models, digital twins enable continuous monitoring, simulation, prediction, and optimization, effectively bridging the gap between the physical and digital worlds. Recent advancements in communication, comp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02167v1-abstract-full').style.display = 'inline'; document.getElementById('2503.02167v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.02167v1-abstract-full" style="display: none;"> Digital twin technology is a transformative innovation driving the digital transformation and intelligent optimization of manufacturing systems. By integrating real-time data with computational models, digital twins enable continuous monitoring, simulation, prediction, and optimization, effectively bridging the gap between the physical and digital worlds. Recent advancements in communication, computing, and control technologies have accelerated the development and adoption of digital twins across various industries. However, significant challenges remain, including limited data for accurate system modeling, inefficiencies in system analysis, and a lack of explainability in the interactions between physical and digital systems. The rise of large language models (LLMs) offers new avenues to address these challenges. LLMs have shown exceptional capabilities across diverse domains, exhibiting strong generalization and emergent abilities that hold great potential for enhancing digital twins. This paper provides a comprehensive review of recent developments in LLMs and their applications to digital twin modeling. We propose a unified description-prediction-prescription framework to integrate digital twin modeling technologies and introduce a structured taxonomy to categorize LLM functionalities in these contexts. For each stage of application, we summarize the methodologies, identify key challenges, and explore potential future directions. To demonstrate the effectiveness of LLM-enhanced digital twins, we present an LLM-enhanced enterprise digital twin system, which enables automatic modeling and optimization of an enterprise. Finally, we discuss future opportunities and challenges in advancing LLM-enhanced digital twins, offering valuable insights for researchers and practitioners in related fields. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02167v1-abstract-full').style.display = 'none'; document.getElementById('2503.02167v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <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">19 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.01058">arXiv:2503.01058</a> <span> [<a href="https://arxiv.org/pdf/2503.01058">pdf</a>, <a href="https://arxiv.org/format/2503.01058">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"> General Force Sensation for Tactile Robot </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/cs?searchtype=author&query=Ou%2C+N">Ni Ou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xuyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhiyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yongqiang Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yupeng Wang</a>, <a href="/search/cs?searchtype=author&query=Lepora%2C+N">Nathan Lepora</a>, <a href="/search/cs?searchtype=author&query=Jamone%2C+L">Lorenzo Jamone</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+J">Jiankang Deng</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2503.01058v1-abstract-short" style="display: inline;"> Robotic tactile sensors, including vision-based and taxel-based sensors, enable agile manipulation and safe human-robot interaction through force sensation. However, variations in structural configurations, measured signals, and material properties create domain gaps that limit the transferability of learned force sensation across different tactile sensors. Here, we introduce GenForce, a general f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.01058v1-abstract-full').style.display = 'inline'; document.getElementById('2503.01058v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.01058v1-abstract-full" style="display: none;"> Robotic tactile sensors, including vision-based and taxel-based sensors, enable agile manipulation and safe human-robot interaction through force sensation. However, variations in structural configurations, measured signals, and material properties create domain gaps that limit the transferability of learned force sensation across different tactile sensors. Here, we introduce GenForce, a general framework for achieving transferable force sensation across both homogeneous and heterogeneous tactile sensors in robotic systems. By unifying tactile signals into marker-based binary tactile images, GenForce enables the transfer of existing force labels to arbitrary target sensors using a marker-to-marker translation technique with a few paired data. This process equips uncalibrated tactile sensors with force prediction capabilities through spatiotemporal force prediction models trained on the transferred data. Extensive experimental results validate GenForce's generalizability, accuracy, and robustness across sensors with diverse marker patterns, structural designs, material properties, and sensing principles. The framework significantly reduces the need for costly and labor-intensive labeled data collection, enabling the rapid deployment of multiple tactile sensors on robotic hands requiring force sensing capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.01058v1-abstract-full').style.display = 'none'; document.getElementById('2503.01058v1-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> 2 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.16190">arXiv:2502.16190</a> <span> [<a href="https://arxiv.org/pdf/2502.16190">pdf</a>, <a href="https://arxiv.org/format/2502.16190">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> AdaNDV: Adaptive Number of Distinct Value Estimation via Learning to Select and Fuse Estimators </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xianghong Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tieying Zhang</a>, <a href="/search/cs?searchtype=author&query=He%2C+X">Xiao He</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoyang Li</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+R">Rong Kang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuai Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Linhui Xu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Z">Zhimin Liang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shangyu Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lei Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jianjun 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="2502.16190v2-abstract-short" style="display: inline;"> Estimating the Number of Distinct Values (NDV) is fundamental for numerous data management tasks, especially within database applications. However, most existing works primarily focus on introducing new statistical or learned estimators, while identifying the most suitable estimator for a given scenario remains largely unexplored. Therefore, we propose AdaNDV, a learned method designed to adaptive… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16190v2-abstract-full').style.display = 'inline'; document.getElementById('2502.16190v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.16190v2-abstract-full" style="display: none;"> Estimating the Number of Distinct Values (NDV) is fundamental for numerous data management tasks, especially within database applications. However, most existing works primarily focus on introducing new statistical or learned estimators, while identifying the most suitable estimator for a given scenario remains largely unexplored. Therefore, we propose AdaNDV, a learned method designed to adaptively select and fuse existing estimators to address this issue. Specifically, (1) we propose to use learned models to distinguish between overestimated and underestimated estimators and then select appropriate estimators from each category. This strategy provides a complementary perspective by integrating overestimations and underestimations for error correction, thereby improving the accuracy of NDV estimation. (2) To further integrate the estimation results, we introduce a novel fusion approach that employs a learned model to predict the weights of the selected estimators and then applies a weighted sum to merge them. By combining these strategies, the proposed AdaNDV fundamentally distinguishes itself from previous works that directly estimate NDV. Moreover, extensive experiments conducted on real-world datasets, with the number of individual columns being several orders of magnitude larger than in previous studies, demonstrate the superior performance of our method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16190v2-abstract-full').style.display = 'none'; document.getElementById('2502.16190v2-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> 2 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 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 by VLDB 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/2502.06101">arXiv:2502.06101</a> <span> [<a href="https://arxiv.org/pdf/2502.06101">pdf</a>, <a href="https://arxiv.org/format/2502.06101">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jian Xu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sichun Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiangyu Chen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Haoming Huang</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+H">Hanxu Hou</a>, <a href="/search/cs?searchtype=author&query=Song%2C+L">Linqi Song</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="2502.06101v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items and improve system performance. However, existing RAG methods rely primarily on textual semantics and often fail to incorporate the most relevant items, lim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06101v2-abstract-full').style.display = 'inline'; document.getElementById('2502.06101v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.06101v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items and improve system performance. However, existing RAG methods rely primarily on textual semantics and often fail to incorporate the most relevant items, limiting the effectiveness of the systems. In this paper, we propose Representation learning for retrieval-Augmented Large Language model Recommendation (RALLRec). Specifically, we enhance textual semantics by prompting LLMs to generate more detailed item descriptions, followed by joint representation learning of textual and collaborative semantics, which are extracted by the LLM and recommendation models, respectively. Considering the potential time-varying characteristics of user interest, a simple yet effective reranking method is further introduced to capture the dynamics of user preference. We conducted extensive experiments on three real-world datasets, and the evaluation results validated the effectiveness of our method. Code is made public at https://github.com/JianXu95/RALLRec. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06101v2-abstract-full').style.display = 'none'; document.getElementById('2502.06101v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 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 by TheWebConf'25 (WWW'25) as a Short Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.02025">arXiv:2502.02025</a> <span> [<a href="https://arxiv.org/pdf/2502.02025">pdf</a>, <a href="https://arxiv.org/format/2502.02025">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"> From Accidents to Insights: Leveraging Multimodal Data for Scenario-Driven ADS Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siwei Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Yao Deng</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+X">Xi Zheng</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="2502.02025v1-abstract-short" style="display: inline;"> The rapid advancements in Autonomous Driving Systems (ADS) have necessitated robust software testing to ensure safety and reliability. However, automating the generation of scalable and concrete test scenarios remains a significant challenge. Current scenario-based test case generation methods often face limitations, such as unrealistic scenes and inaccurate vehicle trajectories. These challenges… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02025v1-abstract-full').style.display = 'inline'; document.getElementById('2502.02025v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.02025v1-abstract-full" style="display: none;"> The rapid advancements in Autonomous Driving Systems (ADS) have necessitated robust software testing to ensure safety and reliability. However, automating the generation of scalable and concrete test scenarios remains a significant challenge. Current scenario-based test case generation methods often face limitations, such as unrealistic scenes and inaccurate vehicle trajectories. These challenges largely result from the loss of map information during data extraction and the lack of an effective verification mechanism to mitigate hallucinations in large language models (LLMs). This paper introduces TRACE, a scenario-based ADS Test case Generation framework for Critical Scenarios. By leveraging multimodal data to extract challenging scenarios from real-world car crash reports, TRACE constructs numerous critical test cases with less data, significantly enhancing ADS bug detection efficiency. Using in-context learning, chain-of-thought prompting, and self-validation approaches, we use LLMs to extract environmental and road network information from crash reports. For vehicle trajectory planning, data containing map information and vehicle coordinates serves as a knowledge base to build a ChatGPT-based LLM with path-planning capabilities, which we named TrackMate. Based on 50 existing crash reports, our approach successfully tested three ADS models across two simulation platforms, MetaDrive and BeamNG. Of the 290 constructed test scenarios, 127 are identified as critical, as they resulted in vehicle collisions. Additionally, user feedback reveals that TRACE demonstrates superior scenario reconstruction accuracy, with 77.5% of the scenarios being rated as 'mostly or 'totally' consistent, compared to only 27% for the most related SOTA, LCTGen. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02025v1-abstract-full').style.display = 'none'; document.getElementById('2502.02025v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 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/2501.16823">arXiv:2501.16823</a> <span> [<a href="https://arxiv.org/pdf/2501.16823">pdf</a>, <a href="https://arxiv.org/format/2501.16823">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"> Phase Noise Resilient Codebook Design for Sparse Code Multiple Access </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+H">Haibo Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Q">Qu Luo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zilong Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+P">Pei Xiao</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiaojun Yuan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.16823v1-abstract-short" style="display: inline;"> Sparse code multiple access (SCMA) is a promising technique for future machine type communication systems due to its superior spectral efficiency and capability for supporting massive connectivity. This paper proposes a novel class of sparse codebooks to improve the error rate performance of SCMA in the presence of phase noise (PN). Specifically, we first analyze the error rate performance of SCMA… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16823v1-abstract-full').style.display = 'inline'; document.getElementById('2501.16823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.16823v1-abstract-full" style="display: none;"> Sparse code multiple access (SCMA) is a promising technique for future machine type communication systems due to its superior spectral efficiency and capability for supporting massive connectivity. This paper proposes a novel class of sparse codebooks to improve the error rate performance of SCMA in the presence of phase noise (PN). Specifically, we first analyze the error rate performance of SCMA impaired by looking into the pair-wise error probability. Then, a novel codebook design metric, called minimum PN metric (MPNM), is proposed. In addition, to design PN resilient codebooks, we propose a novel pulse-amplitude modulation (PAM)-based low projection mother constellation (LP-MC), called LP-PAM. The codebooks for different users are obtained by rotating and scaling the MC, where the phase rotation angles and scaling factors for different users are optimized by maximizing the proposed MPNM. Numerical results show that the proposed PNCBs have larger MPNM values and achieve improved error rate performance than the-state-of-the-art codebooks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16823v1-abstract-full').style.display = 'none'; document.getElementById('2501.16823v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.16759">arXiv:2501.16759</a> <span> [<a href="https://arxiv.org/pdf/2501.16759">pdf</a>, <a href="https://arxiv.org/format/2501.16759">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Are Joins over LSM-trees Ready: Take RocksDB as an Example </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+W">Weiping Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fan Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xuwei Zhang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siqiang Luo</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="2501.16759v2-abstract-short" style="display: inline;"> LSM-tree-based data stores are widely adopted in industries for their excellent performance. As data scales increase, disk-based join operations become indispensable yet costly for the database, making the selection of suitable join methods crucial for system optimization. Current LSM-based stores generally adhere to conventional relational database practices and support only a limited number of j… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16759v2-abstract-full').style.display = 'inline'; document.getElementById('2501.16759v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.16759v2-abstract-full" style="display: none;"> LSM-tree-based data stores are widely adopted in industries for their excellent performance. As data scales increase, disk-based join operations become indispensable yet costly for the database, making the selection of suitable join methods crucial for system optimization. Current LSM-based stores generally adhere to conventional relational database practices and support only a limited number of join methods. However, the LSM-tree delivers distinct read and write efficiency compared to the relational databases, which could accordingly impact the performance of various join methods. Therefore, it is necessary to reconsider the selection of join methods in this context to fully explore the potential of various join algorithms and index designs. In this work, we present a systematic study and an exhaustive benchmark for joins over LSM-trees. We define a configuration space for join methods, encompassing various join algorithms, secondary index types, and consistency strategies. We also summarize a theoretical analysis to evaluate the overhead of each join method for an in-depth understanding. Furthermore, we implement all join methods in the configuration space on a unified platform and compare their performance through extensive experiments. Our theoretical and experimental results yield several insights and takeaways tailored to joins in LSM-based stores that aid developers in choosing proper join methods based on their working conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16759v2-abstract-full').style.display = 'none'; document.getElementById('2501.16759v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by VLDB 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/2501.07430">arXiv:2501.07430</a> <span> [<a href="https://arxiv.org/pdf/2501.07430">pdf</a>, <a href="https://arxiv.org/format/2501.07430">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"> Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xiyue Zhu</a>, <a href="/search/cs?searchtype=author&query=Kwark%2C+D+H">Dou Hoon Kwark</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+R">Ruike Zhu</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+K">Kaiwen Hong</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Y">Yiqi Tao</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shirui Luo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yudu Li</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Z">Zhi-Pei Liang</a>, <a href="/search/cs?searchtype=author&query=Kindratenko%2C+V">Volodymyr Kindratenko</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="2501.07430v2-abstract-short" style="display: inline;"> In volume-to-volume translations in medical images, existing models often struggle to capture the inherent volumetric distribution using 3D voxelspace representations, due to high computational dataset demands. We present Score-Fusion, a novel volumetric translation model that effectively learns 3D representations by ensembling perpendicularly trained 2D diffusion models in score function space. B… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07430v2-abstract-full').style.display = 'inline'; document.getElementById('2501.07430v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07430v2-abstract-full" style="display: none;"> In volume-to-volume translations in medical images, existing models often struggle to capture the inherent volumetric distribution using 3D voxelspace representations, due to high computational dataset demands. We present Score-Fusion, a novel volumetric translation model that effectively learns 3D representations by ensembling perpendicularly trained 2D diffusion models in score function space. By carefully initializing our model to start with an average of 2D models as in TPDM, we reduce 3D training to a fine-tuning process and thereby mitigate both computational and data demands. Furthermore, we explicitly design the 3D model's hierarchical layers to learn ensembles of 2D features, further enhancing efficiency and performance. Moreover, Score-Fusion naturally extends to multi-modality settings, by fusing diffusion models conditioned on different inputs for flexible, accurate integration. We demonstrate that 3D representation is essential for better performance in downstream recognition tasks, such as tumor segmentation, where most segmentation models are based on 3D representation. Extensive experiments demonstrate that Score-Fusion achieves superior accuracy and volumetric fidelity in 3D medical image super-resolution and modality translation. Beyond these improvements, our work also provides broader insight into learning-based approaches for score function fusion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07430v2-abstract-full').style.display = 'none'; document.getElementById('2501.07430v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.06570">arXiv:2501.06570</a> <span> [<a href="https://arxiv.org/pdf/2501.06570">pdf</a>, <a href="https://arxiv.org/format/2501.06570">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Aster: Enhancing LSM-structures for Scalable Graph Database </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mo%2C+D">Dingheng Mo</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Junfeng Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fan Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siqiang Luo</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="2501.06570v1-abstract-short" style="display: inline;"> There is a proliferation of applications requiring the management of large-scale, evolving graphs under workloads with intensive graph updates and lookups. Driven by this challenge, we introduce Poly-LSM, a high-performance key-value storage engine for graphs with the following novel techniques: (1) Poly-LSM is embedded with a new design of graph-oriented LSM-tree structure that features a hybrid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06570v1-abstract-full').style.display = 'inline'; document.getElementById('2501.06570v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.06570v1-abstract-full" style="display: none;"> There is a proliferation of applications requiring the management of large-scale, evolving graphs under workloads with intensive graph updates and lookups. Driven by this challenge, we introduce Poly-LSM, a high-performance key-value storage engine for graphs with the following novel techniques: (1) Poly-LSM is embedded with a new design of graph-oriented LSM-tree structure that features a hybrid storage model for concisely and effectively storing graph data. (2) Poly-LSM utilizes an adaptive mechanism to handle edge insertions and deletions on graphs with optimized I/O efficiency. (3) Poly-LSM exploits the skewness of graph data to encode the key-value entries. Building upon this foundation, we further implement Aster, a robust and versatile graph database that supports Gremlin query language facilitating various graph applications. In our experiments, we compared Aster against several mainstream real-world graph databases. The results demonstrate that Aster outperforms all baseline graph databases, especially on large-scale graphs. Notably, on the billion-scale Twitter graph dataset, Aster achieves up to 17x throughput improvement compared to the best-performing baseline graph system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06570v1-abstract-full').style.display = 'none'; document.getElementById('2501.06570v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by SIGMOD 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/2501.02471">arXiv:2501.02471</a> <span> [<a href="https://arxiv.org/pdf/2501.02471">pdf</a>, <a href="https://arxiv.org/format/2501.02471">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"> Hengqin-RA-v1: Advanced Large Language Model for Diagnosis and Treatment of Rheumatoid Arthritis with Dataset based Traditional Chinese Medicine </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yishen Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shengda Luo</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+Z">Zishao Zhong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+T">Tongtong Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianguo Zhang</a>, <a href="/search/cs?searchtype=author&query=Ou%2C+P">Peiyao Ou</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yong Liang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Liang Liu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+H">Hudan Pan</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="2501.02471v1-abstract-short" style="display: inline;"> Large language models (LLMs) primarily trained on English texts, often face biases and inaccuracies in Chinese contexts. Their limitations are pronounced in fields like Traditional Chinese Medicine (TCM), where cultural and clinical subtleties are vital, further hindered by a lack of domain-specific data, such as rheumatoid arthritis (RA). To address these issues, this paper introduces Hengqin-RA-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02471v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02471v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02471v1-abstract-full" style="display: none;"> Large language models (LLMs) primarily trained on English texts, often face biases and inaccuracies in Chinese contexts. Their limitations are pronounced in fields like Traditional Chinese Medicine (TCM), where cultural and clinical subtleties are vital, further hindered by a lack of domain-specific data, such as rheumatoid arthritis (RA). To address these issues, this paper introduces Hengqin-RA-v1, the first large language model specifically tailored for TCM with a focus on diagnosing and treating RA. We also present HQ-GCM-RA-C1, a comprehensive RA-specific dataset curated from ancient Chinese medical literature, classical texts, and modern clinical studies. This dataset empowers Hengqin-RA-v1 to deliver accurate and culturally informed responses, effectively bridging the gaps left by general-purpose models. Extensive experiments demonstrate that Hengqin-RA-v1 outperforms state-of-the-art models, even surpassing the diagnostic accuracy of TCM practitioners in certain cases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02471v1-abstract-full').style.display = 'none'; document.getElementById('2501.02471v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 5 figures, AAAI-2025 Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02303">arXiv:2501.02303</a> <span> [<a href="https://arxiv.org/pdf/2501.02303">pdf</a>, <a href="https://arxiv.org/format/2501.02303">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Design and Benchmarking of A Multi-Modality Sensor for Robotic Manipulation with GAN-Based Cross-Modality Interpretation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Dandan Zhang</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+W">Wen Fan</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J">Jialin Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoran Li</a>, <a href="/search/cs?searchtype=author&query=Cong%2C+Q">Qingzheng Cong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weiru Liu</a>, <a href="/search/cs?searchtype=author&query=Lepora%2C+N+F">Nathan F. Lepora</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</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="2501.02303v1-abstract-short" style="display: inline;"> In this paper, we present the design and benchmark of an innovative sensor, ViTacTip, which fulfills the demand for advanced multi-modal sensing in a compact design. A notable feature of ViTacTip is its transparent skin, which incorporates a `see-through-skin' mechanism. This mechanism aims at capturing detailed object features upon contact, significantly improving both vision-based and proximity… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02303v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02303v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02303v1-abstract-full" style="display: none;"> In this paper, we present the design and benchmark of an innovative sensor, ViTacTip, which fulfills the demand for advanced multi-modal sensing in a compact design. A notable feature of ViTacTip is its transparent skin, which incorporates a `see-through-skin' mechanism. This mechanism aims at capturing detailed object features upon contact, significantly improving both vision-based and proximity perception capabilities. In parallel, the biomimetic tips embedded in the sensor's skin are designed to amplify contact details, thus substantially augmenting tactile and derived force perception abilities. To demonstrate the multi-modal capabilities of ViTacTip, we developed a multi-task learning model that enables simultaneous recognition of hardness, material, and textures. To assess the functionality and validate the versatility of ViTacTip, we conducted extensive benchmarking experiments, including object recognition, contact point detection, pose regression, and grating identification. To facilitate seamless switching between various sensing modalities, we employed a Generative Adversarial Network (GAN)-based approach. This method enhances the applicability of the ViTacTip sensor across diverse environments by enabling cross-modality interpretation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02303v1-abstract-full').style.display = 'none'; document.getElementById('2501.02303v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Transactions on Robotics</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.01668">arXiv:2501.01668</a> <span> [<a href="https://arxiv.org/pdf/2501.01668">pdf</a>, <a href="https://arxiv.org/format/2501.01668">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"> CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Bohan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaokang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jing Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jifan Yu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sijia Luo</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jie 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="2501.01668v1-abstract-short" style="display: inline;"> Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01668v1-abstract-full').style.display = 'inline'; document.getElementById('2501.01668v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01668v1-abstract-full" style="display: none;"> Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses, even when all candidate responses are flawed. To enable a lightweight and cost-effective implementation, we introduce an automated data generation pipeline that creates diverse training data. This allows smaller LLMs trained on this data to improve the inference accuracy of larger models, including API-based LLMs. Experimental results across four benchmark datasets with seven policy models demonstrate that our method significantly enhances performance, with gains of 11.8% for Llama3-8B and 10.3% for GPT-4o on the MATH dataset. The corresponding training data and code are publicly available on https://github.com/RUCKBReasoning/CoT-based-Synthesizer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01668v1-abstract-full').style.display = 'none'; document.getElementById('2501.01668v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.01054">arXiv:2501.01054</a> <span> [<a href="https://arxiv.org/pdf/2501.01054">pdf</a>, <a href="https://arxiv.org/format/2501.01054">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="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Dynamic Scaling of Unit Tests for Code Reward Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+Z">Zeyao Ma</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiaokang Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jing Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jifan Yu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sijia Luo</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jie 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="2501.01054v1-abstract-short" style="display: inline;"> Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confident… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01054v1-abstract-full').style.display = 'inline'; document.getElementById('2501.01054v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01054v1-abstract-full" style="display: none;"> Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01054v1-abstract-full').style.display = 'none'; document.getElementById('2501.01054v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">Homepage: https://code-reward-model.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/2412.19990">arXiv:2412.19990</a> <span> [<a href="https://arxiv.org/pdf/2412.19990">pdf</a>, <a href="https://arxiv.org/format/2412.19990">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> SegKAN: High-Resolution Medical Image Segmentation with Long-Distance Dependencies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tan%2C+S">Shengbo Tan</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+R">Rundong Xue</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shipeng Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zeyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinran Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lei Zhang</a>, <a href="/search/cs?searchtype=author&query=Ergu%2C+D">Daji Ergu</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+Z">Zhang Yi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yang Zhao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Y">Ying Cai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.19990v2-abstract-short" style="display: inline;"> Hepatic vessels in computed tomography scans often suffer from image fragmentation and noise interference, making it difficult to maintain vessel integrity and posing significant challenges for vessel segmentation. To address this issue, we propose an innovative model: SegKAN. First, we improve the conventional embedding module by adopting a novel convolutional network structure for image embeddin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19990v2-abstract-full').style.display = 'inline'; document.getElementById('2412.19990v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.19990v2-abstract-full" style="display: none;"> Hepatic vessels in computed tomography scans often suffer from image fragmentation and noise interference, making it difficult to maintain vessel integrity and posing significant challenges for vessel segmentation. To address this issue, we propose an innovative model: SegKAN. First, we improve the conventional embedding module by adopting a novel convolutional network structure for image embedding, which smooths out image noise and prevents issues such as gradient explosion in subsequent stages. Next, we transform the spatial relationships between Patch blocks into temporal relationships to solve the problem of capturing positional relationships between Patch blocks in traditional Vision Transformer models. We conducted experiments on a Hepatic vessel dataset, and compared to the existing state-of-the-art model, the Dice score improved by 1.78%. These results demonstrate that the proposed new structure effectively enhances the segmentation performance of high-resolution extended objects. Code will be available at https://github.com/goblin327/SegKAN <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19990v2-abstract-full').style.display = 'none'; document.getElementById('2412.19990v2-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> 2 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16859">arXiv:2412.16859</a> <span> [<a href="https://arxiv.org/pdf/2412.16859">pdf</a>, <a href="https://arxiv.org/format/2412.16859">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"> Adversarial Diffusion Model for Unsupervised Domain-Adaptive Semantic Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jongmin Yu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Z">Zhongtian Sun</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</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="2412.16859v1-abstract-short" style="display: inline;"> Semantic segmentation requires labour-intensive labelling tasks to obtain the supervision signals, and because of this issue, it is encouraged that using domain adaptation, which transfers information from the existing labelled source domains to unlabelled or weakly labelled target domains, is essential. However, it is intractable to find a well-generalised representation which can describe two do… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16859v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16859v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16859v1-abstract-full" style="display: none;"> Semantic segmentation requires labour-intensive labelling tasks to obtain the supervision signals, and because of this issue, it is encouraged that using domain adaptation, which transfers information from the existing labelled source domains to unlabelled or weakly labelled target domains, is essential. However, it is intractable to find a well-generalised representation which can describe two domains due to probabilistic or geometric difference between the two domains. This paper presents a novel method, the Conditional and Inter-coder Connected Latent Diffusion (CICLD) based Semantic Segmentation Model, to advance unsupervised domain adaptation (UDA) for semantic segmentation tasks. Leveraging the strengths of latent diffusion models and adversarial learning, our method effectively bridges the gap between synthetic and real-world imagery. CICLD incorporates a conditioning mechanism to improve contextual understanding during segmentation and an inter-coder connection to preserve fine-grained details and spatial hierarchies. Additionally, adversarial learning aligns latent feature distributions across source, mixed, and target domains, further enhancing generalisation. Extensive experiments are conducted across three benchmark datasets-GTA5, Synthia, and Cityscape-shows that CICLD outperforms state-of-the-art UDA methods. Notably, the proposed method achieves a mean Intersection over Union (mIoU) of 74.4 for the GTA5 to Cityscape UDA setting and 67.2 mIoU for the Synthia to Cityscape UDA setting. This project is publicly available on 'https://github.com/andreYoo/CICLD'. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16859v1-abstract-full').style.display = 'none'; document.getElementById('2412.16859v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.09635">arXiv:2412.09635</a> <span> [<a href="https://arxiv.org/pdf/2412.09635">pdf</a>, <a href="https://arxiv.org/format/2412.09635">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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"> Integrating Functionalities To A System Via Autoencoder Hippocampus Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siwei Luo</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="2412.09635v1-abstract-short" style="display: inline;"> Integrating multiple functionalities into a system poses a fascinating challenge to the field of deep learning. While the precise mechanisms by which the brain encodes and decodes information, and learns diverse skills, remain elusive, memorization undoubtedly plays a pivotal role in this process. In this article, we delve into the implementation and application of an autoencoder-inspired hippocam… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09635v1-abstract-full').style.display = 'inline'; document.getElementById('2412.09635v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.09635v1-abstract-full" style="display: none;"> Integrating multiple functionalities into a system poses a fascinating challenge to the field of deep learning. While the precise mechanisms by which the brain encodes and decodes information, and learns diverse skills, remain elusive, memorization undoubtedly plays a pivotal role in this process. In this article, we delve into the implementation and application of an autoencoder-inspired hippocampus network in a multi-functional system. We propose an autoencoder-based memorization method for policy function's parameters. Specifically, the encoder of the autoencoder maps policy function's parameters to a skill vector, while the decoder retrieves the parameters via this skill vector. The policy function is dynamically adjusted tailored to corresponding tasks. Henceforth, a skill vectors graph neural network is employed to represent the homeomorphic topological structure of subtasks and manage subtasks execution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.09635v1-abstract-full').style.display = 'none'; document.getElementById('2412.09635v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04738">arXiv:2412.04738</a> <span> [<a href="https://arxiv.org/pdf/2412.04738">pdf</a>, <a href="https://arxiv.org/format/2412.04738">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"> DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liao%2C+N">Ningyi Liao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zihao Yu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siqiang Luo</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="2412.04738v1-abstract-short" style="display: inline;"> Graph Transformer (GT) has recently emerged as a promising neural network architecture for learning graph-structured data. However, its global attention mechanism with quadratic complexity concerning the graph scale prevents wider application to large graphs. While current methods attempt to enhance GT scalability by altering model architecture or encoding hierarchical graph data, our analysis rev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04738v1-abstract-full').style.display = 'inline'; document.getElementById('2412.04738v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04738v1-abstract-full" style="display: none;"> Graph Transformer (GT) has recently emerged as a promising neural network architecture for learning graph-structured data. However, its global attention mechanism with quadratic complexity concerning the graph scale prevents wider application to large graphs. While current methods attempt to enhance GT scalability by altering model architecture or encoding hierarchical graph data, our analysis reveals that these models still suffer from the computational bottleneck related to graph-scale operations. In this work, we target the GT scalability issue and propose DHIL-GT, a scalable Graph Transformer that simplifies network learning by fully decoupling the graph computation to a separate stage in advance. DHIL-GT effectively retrieves hierarchical information by exploiting the graph labeling technique, as we show that the graph label hierarchy is more informative than plain adjacency by offering global connections while promoting locality, and is particularly suitable for handling complex graph patterns such as heterophily. We further design subgraph sampling and positional encoding schemes for precomputing model input on top of graph labels in an end-to-end manner. The training stage thus favorably removes graph-related computations, leading to ideal mini-batch capability and GPU utilization. Notably, the precomputation and training processes of DHIL-GT achieve complexities linear to the number of graph edges and nodes, respectively. Extensive experiments demonstrate that DHIL-GT is efficient in terms of computational boost and mini-batch capability over existing scalable Graph Transformer designs on large-scale benchmarks, while achieving top-tier effectiveness on both homophilous and heterophilous graphs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04738v1-abstract-full').style.display = 'none'; document.getElementById('2412.04738v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03353">arXiv:2412.03353</a> <span> [<a href="https://arxiv.org/pdf/2412.03353">pdf</a>, <a href="https://arxiv.org/format/2412.03353">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"> MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+S">Songbo Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shixin Luo</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jun Wu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Q">Qiuguo Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.03353v1-abstract-short" style="display: inline;"> Legged robots possess inherent advantages in traversing complex 3D terrains. However, previous work on low-cost quadruped robots with egocentric vision systems has been limited by a narrow front-facing view and exteroceptive noise, restricting omnidirectional mobility in such environments. While building a voxel map through a hierarchical structure can refine exteroception processing, it introduce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03353v1-abstract-full').style.display = 'inline'; document.getElementById('2412.03353v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03353v1-abstract-full" style="display: none;"> Legged robots possess inherent advantages in traversing complex 3D terrains. However, previous work on low-cost quadruped robots with egocentric vision systems has been limited by a narrow front-facing view and exteroceptive noise, restricting omnidirectional mobility in such environments. While building a voxel map through a hierarchical structure can refine exteroception processing, it introduces significant computational overhead, noise, and delays. In this paper, we present MOVE, a one-stage end-to-end learning framework capable of multi-skill omnidirectional legged locomotion with limited view in 3D environments, just like what a real animal can do. When movement aligns with the robot's line of sight, exteroceptive perception enhances locomotion, enabling extreme climbing and leaping. When vision is obstructed or the direction of movement lies outside the robot's field of view, the robot relies on proprioception for tasks like crawling and climbing stairs. We integrate all these skills into a single neural network by introducing a pseudo-siamese network structure combining supervised and contrastive learning which helps the robot infer its surroundings beyond its field of view. Experiments in both simulations and real-world scenarios demonstrate the robustness of our method, broadening the operational environments for robotics with egocentric vision. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03353v1-abstract-full').style.display = 'none'; document.getElementById('2412.03353v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03275">arXiv:2412.03275</a> <span> [<a href="https://arxiv.org/pdf/2412.03275">pdf</a>, <a href="https://arxiv.org/format/2412.03275">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"> AntLM: Bridging Causal and Masked Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xinru Yu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+B">Bin Guo</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shiwei Luo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jie Wang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+T">Tao Ji</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuanbin 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="2412.03275v1-abstract-short" style="display: inline;"> Causal Language Modeling (CLM) and Masked Language Modeling (MLM) are two mainstream learning paradigms based on Transformer networks, specifically the Decoder-only and Encoder-only architectures. The strengths of each paradigm in downstream tasks have shown a mix of advantages and disadvantages. In the past BabyLM Challenge 2023, although the MLM paradigm achieved the best average performance, th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03275v1-abstract-full').style.display = 'inline'; document.getElementById('2412.03275v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03275v1-abstract-full" style="display: none;"> Causal Language Modeling (CLM) and Masked Language Modeling (MLM) are two mainstream learning paradigms based on Transformer networks, specifically the Decoder-only and Encoder-only architectures. The strengths of each paradigm in downstream tasks have shown a mix of advantages and disadvantages. In the past BabyLM Challenge 2023, although the MLM paradigm achieved the best average performance, the CLM paradigm demonstrated significantly faster convergence rates. For the BabyLM Challenge 2024, we propose a novel language modeling paradigm named $\textbf{AntLM}$, which integrates both CLM and MLM to leverage the advantages of these two classic paradigms. We chose the strict-small track and conducted experiments on two foundation models: BabyLlama, representing CLM, and LTG-BERT, representing MLM. During the training process for specific foundation models, we alternate between applying CLM or MLM training objectives and causal or bidirectional attention masks. Experimental results show that combining the two pretraining objectives leverages their strengths, enhancing overall training performance. Under the same epochs, $AntLM_{BabyLlama}$ improves Macro-average by 1%, and $AntLM_{LTG-BERT}$ achieves a 2.2% increase over the baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03275v1-abstract-full').style.display = 'none'; document.getElementById('2412.03275v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CoNLL Shared Task BabyLM Challenge</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00814">arXiv:2412.00814</a> <span> [<a href="https://arxiv.org/pdf/2412.00814">pdf</a>, <a href="https://arxiv.org/format/2412.00814">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> VR-Doh: Hands-on 3D Modeling in Virtual Reality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+Z">Zhaofeng Luo</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Z">Zhitong Cui</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shijian Luo</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+M">Mengyu Chu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Minchen 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="2412.00814v2-abstract-short" style="display: inline;"> We introduce VR-Doh, a hands-on 3D modeling system that enables intuitive creation and manipulation of elastoplastic objects in Virtual Reality (VR). By customizing the Material Point Method (MPM) for real-time simulation of hand-induced large deformations and enhancing 3D Gaussian Splatting for seamless rendering, VR-Doh provides an interactive and immersive 3D modeling experience. Users can natu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00814v2-abstract-full').style.display = 'inline'; document.getElementById('2412.00814v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00814v2-abstract-full" style="display: none;"> We introduce VR-Doh, a hands-on 3D modeling system that enables intuitive creation and manipulation of elastoplastic objects in Virtual Reality (VR). By customizing the Material Point Method (MPM) for real-time simulation of hand-induced large deformations and enhancing 3D Gaussian Splatting for seamless rendering, VR-Doh provides an interactive and immersive 3D modeling experience. Users can naturally sculpt, deform, and edit objects through both contact- and gesture-based hand-object interactions. To achieve real-time performance, our system incorporates localized simulation techniques, particle-level collision handling, and the decoupling of physical and appearance representations, ensuring smooth and responsive interactions. VR-Doh supports both object creation and editing, enabling diverse modeling tasks such as designing food items, characters, and interlocking structures, all resulting in simulation-ready assets. User studies with both novice and experienced participants highlights the system's intuitive design, immersive feedback, and creative potential. Compared to existing geometric modeling tools, VR-Doh offers enhanced accessibility and natural interaction, making it a powerful tool for creative exploration in VR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00814v2-abstract-full').style.display = 'none'; document.getElementById('2412.00814v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.19545">arXiv:2411.19545</a> <span> [<a href="https://arxiv.org/pdf/2411.19545">pdf</a>, <a href="https://arxiv.org/format/2411.19545">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"> A Unified Interaction Control Framework for Safe Robotic Ultrasound Scanning with Human-Intention-Aware Compliance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+X">Xiangjie Yan</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shaqi Luo</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yongpeng Jiang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+M">Mingrui Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Senqiang Zhu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Gao Huang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+S">Shiji Song</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiang Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.19545v1-abstract-short" style="display: inline;"> The ultrasound scanning robot operates in environments where frequent human-robot interactions occur. Most existing control methods for ultrasound scanning address only one specific interaction situation or implement hard switches between controllers for different situations, which compromises both safety and efficiency. In this paper, we propose a unified interaction control framework for ultraso… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19545v1-abstract-full').style.display = 'inline'; document.getElementById('2411.19545v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.19545v1-abstract-full" style="display: none;"> The ultrasound scanning robot operates in environments where frequent human-robot interactions occur. Most existing control methods for ultrasound scanning address only one specific interaction situation or implement hard switches between controllers for different situations, which compromises both safety and efficiency. In this paper, we propose a unified interaction control framework for ultrasound scanning robots capable of handling all common interactions, distinguishing both human-intended and unintended types, and adapting with appropriate compliance. Specifically, the robot suspends or modulates its ongoing main task if the interaction is intended, e.g., when the doctor grasps the robot to lead the end effector actively. Furthermore, it can identify unintended interactions and avoid potential collision in the null space beforehand. Even if that collision has happened, it can become compliant with the collision in the null space and try to reduce its impact on the main task (where the scan is ongoing) kinematically and dynamically. The multiple situations are integrated into a unified controller with a smooth transition to deal with the interactions by exhibiting human-intention-aware compliance. Experimental results validate the framework's ability to cope with all common interactions including intended intervention and unintended collision in a collaborative carotid artery ultrasound scanning task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19545v1-abstract-full').style.display = 'none'; document.getElementById('2411.19545v1-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> 29 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.18463">arXiv:2411.18463</a> <span> [<a href="https://arxiv.org/pdf/2411.18463">pdf</a>, <a href="https://arxiv.org/format/2411.18463">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiahan Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tong Chen</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shitong Luo</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+C">Chaoran Cheng</a>, <a href="/search/cs?searchtype=author&query=Guan%2C+J">Jiaqi Guan</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+R">Ruihan Guo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sheng Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Ge Liu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Jian Peng</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+J">Jianzhu 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="2411.18463v2-abstract-short" style="display: inline;"> Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.18463v2-abstract-full').style.display = 'inline'; document.getElementById('2411.18463v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.18463v2-abstract-full" style="display: none;"> Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the generated peptides must adopt valid geometries due to the constraints of peptide bonds. Third, realistic tasks for peptide drug development are still lacking. To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins. Building on the observation that certain hot spot residues have higher interaction potentials, we first use an energy-based density model to fit and sample these key residues. Next, to ensure proper peptide geometry, we autoregressively extend peptide fragments by estimating dihedral angles between residue frames. Finally, we apply an optimization process to iteratively refine fragment assembly, ensuring correct peptide structures. By combining hot spot sampling with fragment-based extension, our approach enables de novo peptide design tailored to a target protein and allows the incorporation of key hot spot residues into peptide scaffolds. Extensive experiments, including peptide design and peptide scaffold generation, demonstrate the strong potential of PepHAR in computational peptide binder design. Source code will be available at https://github.com/Ced3-han/PepHAR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.18463v2-abstract-full').style.display = 'none'; document.getElementById('2411.18463v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published as a conference paper at 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/2411.15504">arXiv:2411.15504</a> <span> [<a href="https://arxiv.org/pdf/2411.15504">pdf</a>, <a href="https://arxiv.org/format/2411.15504">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Effects of Muscle Synergy during Overhead Work with a Passive Shoulder Exoskeleton: A Case Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tian%2C+J">Jin Tian</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+B">Baichun Wei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chifu Yang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Suo Luo</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+J">Jiadong Feng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Ping Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Changbing Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yingjie Liu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Haiqi Zhu</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+C">Chunzhi Yi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.15504v1-abstract-short" style="display: inline;"> Objective: Shoulder exoskeletons can effectively assist with overhead work. However, their impacts on muscle synergy remain unclear. The objective is to systematically investigate the effects of the shoulder exoskeleton on muscle synergies during overhead work.Methods: Eight male participants were recruited to perform a screwing task both with (Intervention) and without (Normal) the exoskeleton. E… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15504v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15504v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15504v1-abstract-full" style="display: none;"> Objective: Shoulder exoskeletons can effectively assist with overhead work. However, their impacts on muscle synergy remain unclear. The objective is to systematically investigate the effects of the shoulder exoskeleton on muscle synergies during overhead work.Methods: Eight male participants were recruited to perform a screwing task both with (Intervention) and without (Normal) the exoskeleton. Eight muscles were monitored and muscle synergies were extracted using non-negative matrix factorization and electromyographic topographic maps. Results: The number of synergies extracted was the same (n = 2) in both conditions. Specifically, the first synergies in both conditions were identical, with the highest weight of AD and MD; while the second synergies were different between conditions, with highest weight of PM and MD, respectively. As for the first synergy in the Intervention condition, the activation profile significantly decreased, and the average recruitment level and activation duration were significantly lower (p<0.05). The regression analysis for the muscle synergies across conditions shows the changes of muscle synergies did not influence the sparseness of muscle synergies (p=0.7341). In the topographic maps, the mean value exhibited a significant decrease (p<0.001) and the entropy significantly increased (p<0.01). Conclusion: The exoskeleton does not alter the number of synergies and existing major synergies but may induce new synergies. It can also significantly decrease neural activation and may influence the heterogeneity of the distribution of monitored muscle activations. Significance: This study provides insights into the potential mechanisms of exoskeleton-assisted overhead work and guidance on improving the performance of exoskeletons. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15504v1-abstract-full').style.display = 'none'; document.getElementById('2411.15504v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12503">arXiv:2411.12503</a> <span> [<a href="https://arxiv.org/pdf/2411.12503">pdf</a>, <a href="https://arxiv.org/format/2411.12503">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"> ManiSkill-ViTac 2025: Challenge on Manipulation Skill Learning With Vision and Tactile Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+C">Chuanyu Li</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+R">Renjun Dang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhiyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jing Xu</a>, <a href="/search/cs?searchtype=author&query=Kasaei%2C+H">Hamidreza Kasaei</a>, <a href="/search/cs?searchtype=author&query=Calandra%2C+R">Roberto Calandra</a>, <a href="/search/cs?searchtype=author&query=Lepora%2C+N">Nathan Lepora</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a>, <a href="/search/cs?searchtype=author&query=Su%2C+H">Hao Su</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+R">Rui 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="2411.12503v1-abstract-short" style="display: inline;"> This article introduces the ManiSkill-ViTac Challenge 2025, which focuses on learning contact-rich manipulation skills using both tactile and visual sensing. Expanding upon the 2024 challenge, ManiSkill-ViTac 2025 includes 3 independent tracks: tactile manipulation, tactile-vision fusion manipulation, and tactile sensor structure design. The challenge aims to push the boundaries of robotic manipul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12503v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12503v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12503v1-abstract-full" style="display: none;"> This article introduces the ManiSkill-ViTac Challenge 2025, which focuses on learning contact-rich manipulation skills using both tactile and visual sensing. Expanding upon the 2024 challenge, ManiSkill-ViTac 2025 includes 3 independent tracks: tactile manipulation, tactile-vision fusion manipulation, and tactile sensor structure design. The challenge aims to push the boundaries of robotic manipulation skills, emphasizing the integration of tactile and visual data to enhance performance in complex, real-world tasks. Participants will be evaluated using standardized metrics across both simulated and real-world environments, spurring innovations in sensor design and significantly advancing the field of vision-tactile fusion in robotics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12503v1-abstract-full').style.display = 'none'; document.getElementById('2411.12503v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Challenge webpage: https://ai-workshops.github.io/maniskill-vitac-challenge-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/2411.08347">arXiv:2411.08347</a> <span> [<a href="https://arxiv.org/pdf/2411.08347">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> A Chinese Multi-label Affective Computing Dataset Based on Social Media Network Users </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingyi Zhou</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Senlin Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haofan 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="2411.08347v1-abstract-short" style="display: inline;"> Emotion and personality are central elements in understanding human psychological states. Emotions reflect an individual subjective experiences, while personality reveals relatively stable behavioral and cognitive patterns. Existing affective computing datasets often annotate emotion and personality traits separately, lacking fine-grained labeling of micro-emotions and emotion intensity in both si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08347v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08347v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08347v1-abstract-full" style="display: none;"> Emotion and personality are central elements in understanding human psychological states. Emotions reflect an individual subjective experiences, while personality reveals relatively stable behavioral and cognitive patterns. Existing affective computing datasets often annotate emotion and personality traits separately, lacking fine-grained labeling of micro-emotions and emotion intensity in both single-label and multi-label classifications. Chinese emotion datasets are extremely scarce, and datasets capturing Chinese user personality traits are even more limited. To address these gaps, this study collected data from the major social media platform Weibo, screening 11,338 valid users from over 50,000 individuals with diverse MBTI personality labels and acquiring 566,900 posts along with the user MBTI personality tags. Using the EQN method, we compiled a multi-label Chinese affective computing dataset that integrates the same user's personality traits with six emotions and micro-emotions, each annotated with intensity levels. Validation results across multiple NLP classification models demonstrate the dataset strong utility. This dataset is designed to advance machine recognition of complex human emotions and provide data support for research in psychology, education, marketing, finance, and politics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08347v1-abstract-full').style.display = 'none'; document.getElementById('2411.08347v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06160">arXiv:2411.06160</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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"> Expansion Quantization Network: An Efficient Micro-emotion Annotation and Detection Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingyi Zhou</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Senlin Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haofan 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="2411.06160v2-abstract-short" style="display: inline;"> Text emotion detection constitutes a crucial foundation for advancing artificial intelligence from basic comprehension to the exploration of emotional reasoning. Most existing emotion detection datasets rely on manual annotations, which are associated with high costs, substantial subjectivity, and severe label imbalances. This is particularly evident in the inadequate annotation of micro-emotions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06160v2-abstract-full').style.display = 'inline'; document.getElementById('2411.06160v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06160v2-abstract-full" style="display: none;"> Text emotion detection constitutes a crucial foundation for advancing artificial intelligence from basic comprehension to the exploration of emotional reasoning. Most existing emotion detection datasets rely on manual annotations, which are associated with high costs, substantial subjectivity, and severe label imbalances. This is particularly evident in the inadequate annotation of micro-emotions and the absence of emotional intensity representation, which fail to capture the rich emotions embedded in sentences and adversely affect the quality of downstream task completion. By proposing an all-labels and training-set label regression method, we map label values to energy intensity levels, thereby fully leveraging the learning capabilities of machine models and the interdependencies among labels to uncover multiple emotions within samples. This led to the establishment of the Emotion Quantization Network (EQN) framework for micro-emotion detection and annotation. Using five commonly employed sentiment datasets, we conducted comparative experiments with various models, validating the broad applicability of our framework within NLP machine learning models. Based on the EQN framework, emotion detection and annotation are conducted on the GoEmotions dataset. A comprehensive comparison with the results from Google literature demonstrates that the EQN framework possesses a high capability for automatic detection and annotation of micro-emotions. The EQN framework is the first to achieve automatic micro-emotion annotation with energy-level scores, providing strong support for further emotion detection analysis and the quantitative research of emotion computing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06160v2-abstract-full').style.display = 'none'; document.getElementById('2411.06160v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">3.1 There is a misstatement in the EQN Framework section</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02722">arXiv:2411.02722</a> <span> [<a href="https://arxiv.org/pdf/2411.02722">pdf</a>, <a href="https://arxiv.org/format/2411.02722">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"> Multimodal Commonsense Knowledge Distillation for Visual Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shuo Yang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siwen Luo</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S+C">Soyeon Caren Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02722v1-abstract-short" style="display: inline;"> Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in the general Visual Question Answering (VQA). However, these models struggle with VQA questions that require external commonsense knowledge due to the challenges in generating high-quality prompts and the high computational costs of fine-tuning. In this work, we prop… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02722v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02722v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02722v1-abstract-full" style="display: none;"> Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in the general Visual Question Answering (VQA). However, these models struggle with VQA questions that require external commonsense knowledge due to the challenges in generating high-quality prompts and the high computational costs of fine-tuning. In this work, we propose a novel graph-based multimodal commonsense knowledge distillation framework that constructs a unified relational graph over commonsense knowledge, visual objects and questions through a Graph Convolutional Network (GCN) following a teacher-student environment. This proposed framework is flexible with any type of teacher and student models without further fine-tuning, and has achieved competitive performances on the ScienceQA dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02722v1-abstract-full').style.display = 'none'; document.getElementById('2411.02722v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">AAAI 2025 (Accepted, Oral)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01288">arXiv:2411.01288</a> <span> [<a href="https://arxiv.org/pdf/2411.01288">pdf</a>, <a href="https://arxiv.org/format/2411.01288">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> HEXA-MoE: Efficient and Heterogeneous-aware MoE Acceleration with ZERO Computation Redundancy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shuqing Luo</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Jie Peng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pingzhi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tianlong 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="2411.01288v3-abstract-short" style="display: inline;"> Mixture-of-Experts (MoE) has emerged as a practical approach to scale up parameters for the Transformer model to achieve better generalization while maintaining a sub-linear increase in computation overhead. Current MoE models are mainly built with expert parallelism on distributed devices. However, it usually depends on homogeneous devices to deploy and suffers from heavy communication overhead a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01288v3-abstract-full').style.display = 'inline'; document.getElementById('2411.01288v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01288v3-abstract-full" style="display: none;"> Mixture-of-Experts (MoE) has emerged as a practical approach to scale up parameters for the Transformer model to achieve better generalization while maintaining a sub-linear increase in computation overhead. Current MoE models are mainly built with expert parallelism on distributed devices. However, it usually depends on homogeneous devices to deploy and suffers from heavy communication overhead and computation redundancy. In this paper, we explore developing a \texttt{H}eterogeneous-aware \texttt{EX}pert \texttt{A}llocation framework, \textbf{\texttt{HEXA-MoE}}, with significantly enhanced computing efficiency. It contains two components: ($1$) \textit{Expert-Specific Operators}. We replace the typical general matrix multiplication or grouped matrix multiplication interfaces with our operators, which allows the computing to be performed in an in-place manner with \textbf{ZERO} redundancy. ($2$) \textit{Adaptive Data- and Model-Centric Configurations} for different workload scales. Specifically, we introduce a pipeline-shared cache on each device to tackle the heavy memory consumption in the existing data-centric MoE library. Comprehensive experiments on the Swin-MoE benchmark consistently reveal the effectiveness of our \texttt{HEXA-MoE} framework, i.e., reducing $10\%\sim48\%$ memory consumption and achieving $0.5\sim4.3\times$ speed up compared to current state-of-the-art MoE libraries. Furthermore, we examine our \texttt{HEXA-MoE} with heterogeneous devices for both data- and model-centric settings. Promising results show that employing optimal parallel configuration with \texttt{HEXA-MoE} on heterogeneous devices can substantially minimize overall latency. Codes are available at https://github.com/UNITES-Lab/HEXA-MoE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01288v3-abstract-full').style.display = 'none'; document.getElementById('2411.01288v3-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 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/2411.00114">arXiv:2411.00114</a> <span> [<a href="https://arxiv.org/pdf/2411.00114">pdf</a>, <a href="https://arxiv.org/format/2411.00114">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="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Project Sid: Many-agent simulations toward AI civilization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=AL%2C+A">Altera. AL</a>, <a href="/search/cs?searchtype=author&query=Ahn%2C+A">Andrew Ahn</a>, <a href="/search/cs?searchtype=author&query=Becker%2C+N">Nic Becker</a>, <a href="/search/cs?searchtype=author&query=Carroll%2C+S">Stephanie Carroll</a>, <a href="/search/cs?searchtype=author&query=Christie%2C+N">Nico Christie</a>, <a href="/search/cs?searchtype=author&query=Cortes%2C+M">Manuel Cortes</a>, <a href="/search/cs?searchtype=author&query=Demirci%2C+A">Arda Demirci</a>, <a href="/search/cs?searchtype=author&query=Du%2C+M">Melissa Du</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Frankie Li</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shuying Luo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P+Y">Peter Y Wang</a>, <a href="/search/cs?searchtype=author&query=Willows%2C+M">Mathew Willows</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+F">Feitong Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G+R">Guangyu Robert Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00114v1-abstract-short" style="display: inline;"> AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational processes -- have yet to be explored. Here, we demonstrate how 10 - 1000+ AI agents behave and progress within agent societies. We first introduce the PIANO (Parallel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00114v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00114v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00114v1-abstract-full" style="display: none;"> AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational processes -- have yet to be explored. Here, we demonstrate how 10 - 1000+ AI agents behave and progress within agent societies. We first introduce the PIANO (Parallel Information Aggregation via Neural Orchestration) architecture, which enables agents to interact with humans and other agents in real-time while maintaining coherence across multiple output streams. We then evaluate agent performance in agent simulations using civilizational benchmarks inspired by human history. These simulations, set within a Minecraft environment, reveal that agents are capable of meaningful progress -- autonomously developing specialized roles, adhering to and changing collective rules, and engaging in cultural and religious transmission. These preliminary results show that agents can achieve significant milestones towards AI civilizations, opening new avenues for large simulations, agentic organizational intelligence, and integrating AI into human civilizations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00114v1-abstract-full').style.display = 'none'; document.getElementById('2411.00114v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">35 pages, 14 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.24220">arXiv:2410.24220</a> <span> [<a href="https://arxiv.org/pdf/2410.24220">pdf</a>, <a href="https://arxiv.org/ps/2410.24220">ps</a>, <a href="https://arxiv.org/format/2410.24220">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="Quantitative Methods">q-bio.QM</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"> Bridging Geometric States via Geometric Diffusion Bridge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shengjie Luo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yixian Xu</a>, <a href="/search/cs?searchtype=author&query=He%2C+D">Di He</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Shuxin Zheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tie-Yan Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liwei Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.24220v1-abstract-short" style="display: inline;"> The accurate prediction of geometric state evolution in complex systems is critical for advancing scientific domains such as quantum chemistry and material modeling. Traditional experimental and computational methods face challenges in terms of environmental constraints and computational demands, while current deep learning approaches still fall short in terms of precision and generality. In this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24220v1-abstract-full').style.display = 'inline'; document.getElementById('2410.24220v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.24220v1-abstract-full" style="display: none;"> The accurate prediction of geometric state evolution in complex systems is critical for advancing scientific domains such as quantum chemistry and material modeling. Traditional experimental and computational methods face challenges in terms of environmental constraints and computational demands, while current deep learning approaches still fall short in terms of precision and generality. In this work, we introduce the Geometric Diffusion Bridge (GDB), a novel generative modeling framework that accurately bridges initial and target geometric states. GDB leverages a probabilistic approach to evolve geometric state distributions, employing an equivariant diffusion bridge derived by a modified version of Doob's $h$-transform for connecting geometric states. This tailored diffusion process is anchored by initial and target geometric states as fixed endpoints and governed by equivariant transition kernels. Moreover, trajectory data can be seamlessly leveraged in our GDB framework by using a chain of equivariant diffusion bridges, providing a more detailed and accurate characterization of evolution dynamics. Theoretically, we conduct a thorough examination to confirm our framework's ability to preserve joint distributions of geometric states and capability to completely model the underlying dynamics inducing trajectory distributions with negligible error. Experimental evaluations across various real-world scenarios show that GDB surpasses existing state-of-the-art approaches, opening up a new pathway for accurately bridging geometric states and tackling crucial scientific challenges with improved accuracy and applicability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.24220v1-abstract-full').style.display = 'none'; document.getElementById('2410.24220v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">33 pages, 5 tables; NeurIPS 2024 Camera Ready version</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23883">arXiv:2410.23883</a> <span> [<a href="https://arxiv.org/pdf/2410.23883">pdf</a>, <a href="https://arxiv.org/format/2410.23883">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> 'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+R">Rena Gao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xuetong Wu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siwen Luo</a>, <a href="/search/cs?searchtype=author&query=Han%2C+C">Caren Han</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+F">Feng Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23883v1-abstract-short" style="display: inline;"> Out-of-distribution (OOD) detection in multimodal contexts is essential for identifying deviations in combined inputs from different modalities, particularly in applications like open-domain dialogue systems or real-life dialogue interactions. This paper aims to improve the user experience that involves multi-round long dialogues by efficiently detecting OOD dialogues and images. We introduce a no… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23883v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23883v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23883v1-abstract-full" style="display: none;"> Out-of-distribution (OOD) detection in multimodal contexts is essential for identifying deviations in combined inputs from different modalities, particularly in applications like open-domain dialogue systems or real-life dialogue interactions. This paper aims to improve the user experience that involves multi-round long dialogues by efficiently detecting OOD dialogues and images. We introduce a novel scoring framework named Dialogue Image Aligning and Enhancing Framework (DIAEF) that integrates the visual language models with the novel proposed scores that detect OOD in two key scenarios (1) mismatches between the dialogue and image input pair and (2) input pairs with previously unseen labels. Our experimental results, derived from various benchmarks, demonstrate that integrating image and multi-round dialogue OOD detection is more effective with previously unseen labels than using either modality independently. In the presence of mismatched pairs, our proposed score effectively identifies these mismatches and demonstrates strong robustness in long dialogues. This approach enhances domain-aware, adaptive conversational agents and establishes baselines for future studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23883v1-abstract-full').style.display = 'none'; document.getElementById('2410.23883v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 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/2410.13857">arXiv:2410.13857</a> <span> [<a href="https://arxiv.org/pdf/2410.13857">pdf</a>, <a href="https://arxiv.org/format/2410.13857">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> <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"> How Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+G">Guhao Feng</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+K">Kai Yang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yuntian Gu</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+X">Xinyue Ai</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shengjie Luo</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jiacheng Sun</a>, <a href="/search/cs?searchtype=author&query=He%2C+D">Di He</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhenguo Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liwei Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13857v1-abstract-short" style="display: inline;"> Despite the remarkable success of Transformer-based Large Language Models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a significant challenge. In this paper, we conduct a rigorous theoretical analysis of LLMs' mathematical abilities, with a specific focus on their arithmetic performances. We identify numerical precision as a key factor that in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13857v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13857v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13857v1-abstract-full" style="display: none;"> Despite the remarkable success of Transformer-based Large Language Models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a significant challenge. In this paper, we conduct a rigorous theoretical analysis of LLMs' mathematical abilities, with a specific focus on their arithmetic performances. We identify numerical precision as a key factor that influences their effectiveness in mathematical tasks. Our results show that Transformers operating with low numerical precision fail to address arithmetic tasks, such as iterated addition and integer multiplication, unless the model size grows super-polynomially with respect to the input length. In contrast, Transformers with standard numerical precision can efficiently handle these tasks with significantly smaller model sizes. We further support our theoretical findings through empirical experiments that explore the impact of varying numerical precision on arithmetic tasks, providing valuable insights for improving the mathematical reasoning capabilities of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13857v1-abstract-full').style.display = 'none'; document.getElementById('2410.13857v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12609">arXiv:2410.12609</a> <span> [<a href="https://arxiv.org/pdf/2410.12609">pdf</a>, <a href="https://arxiv.org/ps/2410.12609">ps</a>, <a href="https://arxiv.org/format/2410.12609">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"> Towards Graph Foundation Models: The Perspective of Zero-shot Reasoning on Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kai Wang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Siqiang Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.12609v1-abstract-short" style="display: inline;"> Inspired by the success of artificial general intelligence, there is a trend towards developing Graph Foundation Models that excel in generalization across various graph tasks and domains. However, current models often require extensive training or fine-tuning to capture structural and semantic insights on new graphs, which limits their versatility. In this work, we explore graph foundation models… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12609v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12609v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12609v1-abstract-full" style="display: none;"> Inspired by the success of artificial general intelligence, there is a trend towards developing Graph Foundation Models that excel in generalization across various graph tasks and domains. However, current models often require extensive training or fine-tuning to capture structural and semantic insights on new graphs, which limits their versatility. In this work, we explore graph foundation models from the perspective of zero-shot reasoning on Knowledge Graphs (KGs). Our focus is on utilizing KGs as a unified topological structure to tackle diverse tasks, while addressing semantic isolation challenges in KG reasoning to effectively integrate diverse semantic and structural features. This brings us new methodological insights into KG reasoning, as well as high generalizability towards foundation models in practice. Methodologically, we introduce SCORE, a unified graph reasoning framework that effectively generalizes diverse graph tasks using zero-shot learning. At the core of SCORE is semantic conditional message passing, a technique designed to capture both structural and semantic invariances in graphs, with theoretical backing for its expressive power. Practically, we evaluate the zero-shot reasoning capability of SCORE using 38 diverse graph datasets, covering node-level, link-level, and graph-level tasks across multiple domains. Our experiments reveal a substantial performance improvement over prior foundation models and supervised baselines, highlighting the efficacy and adaptability of our approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12609v1-abstract-full').style.display = 'none'; document.getElementById('2410.12609v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 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/2410.11774">arXiv:2410.11774</a> <span> [<a href="https://arxiv.org/pdf/2410.11774">pdf</a>, <a href="https://arxiv.org/format/2410.11774">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"> Fractal Calibration for long-tailed object detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alexandridis%2C+K+P">Konstantinos Panagiotis Alexandridis</a>, <a href="/search/cs?searchtype=author&query=Elezi%2C+I">Ismail Elezi</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+J">Jiankang Deng</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A">Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.11774v3-abstract-short" style="display: inline;"> Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class frequencies of the dataset. However, these techniques focus solely on the frequency statistics and ignore the distribution of the classes in image space, missing imp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11774v3-abstract-full').style.display = 'inline'; document.getElementById('2410.11774v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11774v3-abstract-full" style="display: none;"> Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class frequencies of the dataset. However, these techniques focus solely on the frequency statistics and ignore the distribution of the classes in image space, missing important information. In contrast to them, we propose FRActal CALibration (FRACAL): a novel post-calibration method for long-tailed object detection. FRACAL devises a logit adjustment method that utilises the fractal dimension to estimate how uniformly classes are distributed in image space. During inference, it uses the fractal dimension to inversely downweight the probabilities of uniformly spaced class predictions achieving balance in two axes: between frequent and rare categories, and between uniformly spaced and sparsely spaced classes. FRACAL is a post-processing method and it does not require any training, also it can be combined with many off-the-shelf models such as one-stage sigmoid detectors and two-stage instance segmentation models. FRACAL boosts the rare class performance by up to 8.6% and surpasses all previous methods on LVIS dataset, while showing good generalisation to other datasets such as COCO, V3Det and OpenImages. We provide the code at https://github.com/kostas1515/FRACAL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11774v3-abstract-full').style.display = 'none'; document.getElementById('2410.11774v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR2025 (camera-ready)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.10587">arXiv:2410.10587</a> <span> [<a href="https://arxiv.org/pdf/2410.10587">pdf</a>, <a href="https://arxiv.org/format/2410.10587">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> TopoFR: A Closer Look at Topology Alignment on Face Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dan%2C+J">Jun Dan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+J">Jiankang Deng</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+H">Haoyu Xie</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Siyuan Li</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+B">Baigui Sun</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shan Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.10587v1-abstract-short" style="display: inline;"> The field of face recognition (FR) has undergone significant advancements with the rise of deep learning. Recently, the success of unsupervised learning and graph neural networks has demonstrated the effectiveness of data structure information. Considering that the FR task can leverage large-scale training data, which intrinsically contains significant structure information, we aim to investigate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10587v1-abstract-full').style.display = 'inline'; document.getElementById('2410.10587v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10587v1-abstract-full" style="display: none;"> The field of face recognition (FR) has undergone significant advancements with the rise of deep learning. Recently, the success of unsupervised learning and graph neural networks has demonstrated the effectiveness of data structure information. Considering that the FR task can leverage large-scale training data, which intrinsically contains significant structure information, we aim to investigate how to encode such critical structure information into the latent space. As revealed from our observations, directly aligning the structure information between the input and latent spaces inevitably suffers from an overfitting problem, leading to a structure collapse phenomenon in the latent space. To address this problem, we propose TopoFR, a novel FR model that leverages a topological structure alignment strategy called PTSA and a hard sample mining strategy named SDE. Concretely, PTSA uses persistent homology to align the topological structures of the input and latent spaces, effectively preserving the structure information and improving the generalization performance of FR model. To mitigate the impact of hard samples on the latent space structure, SDE accurately identifies hard samples by automatically computing structure damage score (SDS) for each sample, and directs the model to prioritize optimizing these samples. Experimental results on popular face benchmarks demonstrate the superiority of our TopoFR over the state-of-the-art methods. Code and models are available at: https://github.com/modelscope/facechain/tree/main/face_module/TopoFR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10587v1-abstract-full').style.display = 'none'; document.getElementById('2410.10587v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.10118">arXiv:2410.10118</a> <span> [<a href="https://arxiv.org/pdf/2410.10118">pdf</a>, <a href="https://arxiv.org/format/2410.10118">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="Chemical Physics">physics.chem-ph</span> </div> </div> <p class="title is-5 mathjax"> Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ren%2C+Y">Yuxuan Ren</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+D">Dihan Zheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chang Liu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+P">Peiran Jin</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yu Shi</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+L">Lin Huang</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jiyan He</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shengjie Luo</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+T">Tao Qin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tie-Yan Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.10118v1-abstract-short" style="display: inline;"> In recent years, machine learning has demonstrated impressive capability in handling molecular science tasks. To support various molecular properties at scale, machine learning models are trained in the multi-task learning paradigm. Nevertheless, data of different molecular properties are often not aligned: some quantities, e.g. equilibrium structure, demand more cost to compute than others, e.g.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10118v1-abstract-full').style.display = 'inline'; document.getElementById('2410.10118v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10118v1-abstract-full" style="display: none;"> In recent years, machine learning has demonstrated impressive capability in handling molecular science tasks. To support various molecular properties at scale, machine learning models are trained in the multi-task learning paradigm. Nevertheless, data of different molecular properties are often not aligned: some quantities, e.g. equilibrium structure, demand more cost to compute than others, e.g. energy, so their data are often generated by cheaper computational methods at the cost of lower accuracy, which cannot be directly overcome through multi-task learning. Moreover, it is not straightforward to leverage abundant data of other tasks to benefit a particular task. To handle such data heterogeneity challenges, we exploit the specialty of molecular tasks that there are physical laws connecting them, and design consistency training approaches that allow different tasks to exchange information directly so as to improve one another. Particularly, we demonstrate that the more accurate energy data can improve the accuracy of structure prediction. We also find that consistency training can directly leverage force and off-equilibrium structure data to improve structure prediction, demonstrating a broad capability for integrating heterogeneous data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10118v1-abstract-full').style.display = 'none'; document.getElementById('2410.10118v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published as a conference paper at NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03777">arXiv:2410.03777</a> <span> [<a href="https://arxiv.org/pdf/2410.03777">pdf</a>, <a href="https://arxiv.org/format/2410.03777">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"> Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yuxuan Yao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Han Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mingyang Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Sichun Luo</a>, <a href="/search/cs?searchtype=author&query=Han%2C+X">Xiongwei Han</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jie Liu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Z">Zhijiang Guo</a>, <a href="/search/cs?searchtype=author&query=Song%2C+L">Linqi Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03777v2-abstract-short" style="display: inline;"> Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage their complementary advantages. However, existing LLM ensembling methods often overlook model compatibility and struggle with inefficient alignment of probabilities across the entire vocabulary. In this study, we empirically… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03777v2-abstract-full').style.display = 'inline'; document.getElementById('2410.03777v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03777v2-abstract-full" style="display: none;"> Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage their complementary advantages. However, existing LLM ensembling methods often overlook model compatibility and struggle with inefficient alignment of probabilities across the entire vocabulary. In this study, we empirically investigate the factors influencing ensemble performance, identifying model performance, vocabulary size, and response style as key determinants, revealing that compatibility among models is essential for effective ensembling. This analysis leads to the development of a simple yet effective model selection strategy that identifies compatible models. Additionally, we introduce the \textsc{Uni}on \textsc{T}op-$k$ \textsc{E}nsembling (\textsc{UniTE}), a novel approach that efficiently combines models by focusing on the union of the top-k tokens from each model, thereby avoiding the need for full vocabulary alignment and reducing computational overhead. Extensive evaluations across multiple benchmarks demonstrate that \textsc{UniTE} significantly enhances performance compared to existing methods, offering a more efficient framework for LLM ensembling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03777v2-abstract-full').style.display = 'none'; document.getElementById('2410.03777v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03494">arXiv:2410.03494</a> <span> [<a href="https://arxiv.org/pdf/2410.03494">pdf</a>, <a href="https://arxiv.org/format/2410.03494">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="Chemical Physics">physics.chem-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Generative Artificial Intelligence for Navigating Synthesizable Chemical Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+W">Wenhao Gao</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shitong Luo</a>, <a href="/search/cs?searchtype=author&query=Coley%2C+C+W">Connor W. Coley</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03494v1-abstract-short" style="display: inline;"> We introduce SynFormer, a generative modeling framework designed to efficiently explore and navigate synthesizable chemical space. Unlike traditional molecular generation approaches, we generate synthetic pathways for molecules to ensure that designs are synthetically tractable. By incorporating a scalable transformer architecture and a diffusion module for building block selection, SynFormer surp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03494v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03494v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03494v1-abstract-full" style="display: none;"> We introduce SynFormer, a generative modeling framework designed to efficiently explore and navigate synthesizable chemical space. Unlike traditional molecular generation approaches, we generate synthetic pathways for molecules to ensure that designs are synthetically tractable. By incorporating a scalable transformer architecture and a diffusion module for building block selection, SynFormer surpasses existing models in synthesizable molecular design. We demonstrate SynFormer's effectiveness in two key applications: (1) local chemical space exploration, where the model generates synthesizable analogs of a reference molecule, and (2) global chemical space exploration, where the model aims to identify optimal molecules according to a black-box property prediction oracle. Additionally, we demonstrate the scalability of our approach via the improvement in performance as more computational resources become available. With our code and trained models openly available, we hope that SynFormer will find use across applications in drug discovery and materials science. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03494v1-abstract-full').style.display = 'none'; document.getElementById('2410.03494v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </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=Luo%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Luo%2C+S&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