deploy: VectorDB-NTU/long-vector-website@4914c77

VectorDB-NTU · Nov 23, 2024 · eff973b · eff973b
1 parent 5498bd2
commit eff973b
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/index.html b/index.html
@@ -1,9 +1,9 @@
 <!doctype html><html class=no-js lang=en><head><meta name=generator content="Hugo 0.135.0"><meta charset=UTF-8><meta name=viewport content="width=device-width,initial-scale=1"><meta http-equiv=X-UA-Compatible content="IE=edge"><title>Vector Database Group @ NTU</title>
-<script>(function(e,t){e[t]=e[t].replace("no-js","js")})(document.documentElement,"className")</script><meta name=description content="Welcome to our website!"><meta property="og:url" content="https://VectorDB-NTU.github.io/"><meta property="og:site_name" content="Vector Database Group @ NTU"><meta property="og:title" content="Home"><meta property="og:description" content="About us We are Vector Database Research Group at Nanyang Technological School. Our interests lies in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
-Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:"><meta property="og:locale" content="en"><meta property="og:type" content="website"><meta itemprop=name content="Home"><meta itemprop=description content="About us We are Vector Database Research Group at Nanyang Technological School. Our interests lies in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
-Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:"><meta itemprop=datePublished content="2024-10-12T00:00:00+00:00"><meta itemprop=dateModified content="2024-10-12T00:00:00+00:00"><meta itemprop=wordCount content="149"><meta name=twitter:card content="summary"><meta name=twitter:title content="Home"><meta name=twitter:description content="About us We are Vector Database Research Group at Nanyang Technological School. Our interests lies in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
+<script>(function(e,t){e[t]=e[t].replace("no-js","js")})(document.documentElement,"className")</script><meta name=description content="Welcome to our website!"><meta property="og:url" content="https://VectorDB-NTU.github.io/"><meta property="og:site_name" content="Vector Database Group @ NTU"><meta property="og:title" content="Home"><meta property="og:description" content="About us We are Vector Database Research Group at Nanyang Technological University. Our interests lie in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
+Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:"><meta property="og:locale" content="en"><meta property="og:type" content="website"><meta itemprop=name content="Home"><meta itemprop=description content="About us We are Vector Database Research Group at Nanyang Technological University. Our interests lie in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
+Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:"><meta itemprop=datePublished content="2024-10-12T00:00:00+00:00"><meta itemprop=dateModified content="2024-10-12T00:00:00+00:00"><meta itemprop=wordCount content="149"><meta name=twitter:card content="summary"><meta name=twitter:title content="Home"><meta name=twitter:description content="About us We are Vector Database Research Group at Nanyang Technological University. Our interests lie in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).
 Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:"><link rel=stylesheet href=/css/style.css><link rel=stylesheet href=/css/custom.css><link rel=alternate type=application/rss+xml href=/index.xml title="Vector Database Group @ NTU"><link rel="shortcut icon" href=/favicon.ico></head><body class=body><header class=header><div class="logo logo--mixed"><div class=container><a class=logo__link href=/ title="Vector Database Group @ NTU" rel=home><div class="logo__item logo__imagebox"><img class=logo__img src=/img/NTU_badge.png alt="Logo image"></div><div class="logo__item logo__text"><div class=logo__title>Vector Database Group @ NTU</div><div class=logo__tagline>Nanyang Technological University</div></div></a></div></div></header><nav class=menu><div class=container><button class=menu__btn aria-haspopup=true aria-expanded=false tabindex=0>
-<span class=menu__btn-title tabindex=-1>Menu</span></button><ul class=menu__list><li class="menu__item menu__item--active"><a class=menu__link href=/><span class=menu__text>Home</span></a></li><li class=menu__item><a class=menu__link href=/impacts/><span class=menu__text>Impacts</span></a></li><li class=menu__item><a class=menu__link href=/news/><span class=menu__text>News</span></a></li><li class=menu__item><a class=menu__link href=/publications/><span class=menu__text>Publications</span></a></li><li class=menu__item><a class=menu__link href=/people/><span class=menu__text>People</span></a></li></ul></div></nav><div class="container wrapper flex"><div class=primary><main class="main list" role=main><div class="content main__content clearfix"><h1 id=about-us>About us</h1><p>We are Vector Database Research Group at Nanyang Technological School. Our interests lies in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).</p><p><img src=/img/bigdata.webp alt=bigdata></p><p>Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:</p><ul><li><a href=https://arxiv.org/abs/2411.12229>SymphonyQG for combining graph-based index with quantization</a> (SIGMOD'25)</li><li><a href=https://arxiv.org/abs/2409.09913>Extended RaBitQ for allowing more flexible quantization with varying compression rates</a> (arXiv).</li><li><a href=https://arxiv.org/abs/2409.02571>iRangeGraph for attribute-filtered ANN</a> (SIGMOD'25)</li><li><a href=https://arxiv.org/abs/2405.12497>RaBitQ for quantizing high-dimensional vectors</a> (SIGMOD'24)</li><li><a href=https://arxiv.org/abs/2303.09855>ADSampling for efficient and reliable distance comparisons</a> (SIGMOD'23)</li></ul></div></main></div><aside class=sidebar><div class="widget-search widget"><form class=widget-search__form role=search method=get action=https://duckduckgo.com/><label><input class=widget-search__field type=search placeholder=SEARCH... name=q aria-label=SEARCH...>
+<span class=menu__btn-title tabindex=-1>Menu</span></button><ul class=menu__list><li class="menu__item menu__item--active"><a class=menu__link href=/><span class=menu__text>Home</span></a></li><li class=menu__item><a class=menu__link href=/impacts/><span class=menu__text>Impacts</span></a></li><li class=menu__item><a class=menu__link href=/news/><span class=menu__text>News</span></a></li><li class=menu__item><a class=menu__link href=/publications/><span class=menu__text>Publications</span></a></li><li class=menu__item><a class=menu__link href=/people/><span class=menu__text>People</span></a></li></ul></div></nav><div class="container wrapper flex"><div class=primary><main class="main list" role=main><div class="content main__content clearfix"><h1 id=about-us>About us</h1><p>We are Vector Database Research Group at Nanyang Technological University. Our interests lie in high-dimensional vector data management (and its applications in large models such as retrieval-augmented generative AI).</p><p><img src=/img/bigdata.webp alt=bigdata></p><p>Large-scale high-dimensional vector data has become ubiquitous in contemporary times. For instance, various forms of unstructured data, such as images, videos, texts, and speeches, are typically transformed into vectors using deep learning techniques. These vectors are subsequently employed in downstream analytical tasks. Nearest neighbor (NN) search in high-dimensional vector space constitutes a fundamental problem with a wide array of applications in information retrieval, recommendations, and retrieval-based large language models. We have developed several techniques for approximate NN (ANN), including:</p><ul><li><a href=https://arxiv.org/abs/2409.09913>Extended RaBitQ for allowing more flexible quantization with varying compression rates</a> (arXiv).</li><li><a href=https://arxiv.org/abs/2411.12229>SymphonyQG for combining graph-based index with quantization</a> (SIGMOD'25)</li><li><a href=https://arxiv.org/abs/2409.02571>iRangeGraph for attribute-filtered ANN</a> (SIGMOD'25)</li><li><a href=https://arxiv.org/abs/2405.12497>RaBitQ for quantizing high-dimensional vectors</a> (SIGMOD'24)</li><li><a href=https://arxiv.org/abs/2303.09855>ADSampling for efficient and reliable distance comparisons</a> (SIGMOD'23)</li></ul></div></main></div><aside class=sidebar><div class="widget-search widget"><form class=widget-search__form role=search method=get action=https://duckduckgo.com/><label><input class=widget-search__field type=search placeholder=SEARCH... name=q aria-label=SEARCH...>
 </label><input class=widget-search__submit type=submit value=Search>
 <input type=hidden name=sites value=https://VectorDB-NTU.github.io/></form></div><div class="widget-recent widget"><h4 class=widget__title>Recent Posts</h4><div class=widget__content><ul class=widget__list><li class=widget__item><a class=widget__link href=/news/irange/>iRangeGraph has been accepted by SIGMOD' 25</a></li><li class=widget__item><a class=widget__link href=/news/rabitq/>RaBitQ has been accepted by SIGMOD' 24</a></li><li class=widget__item><a class=widget__link href=/news/adsampling/>ADSampling has been accepted by SIGMOD' 23</a></li></ul></div></div><div class="widget-taglist widget"><h4 class=widget__title>Tags</h4><div class=widget__content><a class="widget-taglist__link widget__link btn" href=/tags/ann-search/ title="ANN Search">ANN Search</a>
 <a class="widget-taglist__link widget__link btn" href=/tags/cooperation/ title=Cooperation>Cooperation</a>