{"id":16330,"date":"2024-02-09T12:43:03","date_gmt":"2024-02-09T03:43:03","guid":{"rendered":"https:\/\/deeplearning.jp\/?p=16330"},"modified":"2024-07-22T12:53:26","modified_gmt":"2024-07-22T03:53:26","slug":"moe-llava-mixture-of-experts-for-largevision-language-models","status":"publish","type":"post","link":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/","title":{"rendered":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models"},"content":{"rendered":"<p><script async class=\"docswell-embed\" src=\"https:\/\/bcdn.docswell.com\/assets\/libs\/docswell-embed\/docswell-embed.min.js\" data-src=\"https:\/\/www.docswell.com\/slide\/538V1L\/embed\" data-aspect=\"0.5625\"><\/script><\/p>\n<div class=\"docswell-link\"><a href=\"https:\/\/www.docswell.com\/s\/DeepLearning2023\/538V1L-2024-02-09-132927\">\u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vision-Language Models by @DeepLearning2023<\/a><\/div>\n<p><\/p>","protected":false},"excerpt":{"rendered":"<p>\u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vision-Language Models by @DeepLearnin <a class=\"read-more\" href=\"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/\"> more <i class=\"fa fa-arrow-right\" aria-hidden=\"true\"><\/i><\/a><\/p>\n","protected":false},"author":43,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[131,109],"tags":[],"class_list":["post-16330","post","type-post","status-publish","format-standard","hentry","category-dls-2024","category-papers"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.4 - aioseo.com -->\n\t<meta name=\"description\" content=\"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Emma Nishioka\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.4\" \/>\n\n\t\t<!-- Google tag (gtag.js) -->\n<script async src=\"https:\/\/www.googletagmanager.com\/gtag\/js?id=G-S7YG337LDD\"><\/script>\n<script>\n  window.dataLayer = window.dataLayer || [];\n  function gtag(){dataLayer.push(arguments);}\n  gtag('js', new Date());\n\n  gtag('config', 'G-S7YG337LDD');\n<\/script>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"Deep Learning JP\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP\" \/>\n\t\t<meta property=\"og:description\" content=\"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"450\" \/>\n\t\t<meta property=\"og:image:height\" content=\"300\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2024-02-09T03:43:03+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2024-07-22T03:53:26+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary\" \/>\n\t\t<meta name=\"twitter:title\" content=\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP\" \/>\n\t\t<meta name=\"twitter:description\" content=\"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis\" \/>\n\t\t<meta name=\"twitter:image\" content=\"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#article\",\"name\":\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP\",\"headline\":\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models\",\"author\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/author\\\/emma-nishioka\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#organization\"},\"datePublished\":\"2024-02-09T12:43:03+09:00\",\"dateModified\":\"2024-07-22T12:53:26+09:00\",\"inLanguage\":\"en-US\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#webpage\"},\"articleSection\":\"dls-2024,\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/#listItem\",\"name\":\"seminar\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/#listItem\",\"position\":2,\"name\":\"seminar\",\"item\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/#listItem\",\"position\":3,\"item\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/dls-2024\\\/#listItem\",\"name\":\"dls-2024\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/#listItem\",\"name\":\"seminar\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/dls-2024\\\/#listItem\",\"position\":4,\"name\":\"dls-2024\",\"item\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/dls-2024\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#listItem\",\"name\":\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#listItem\",\"position\":5,\"name\":\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/category\\\/seminar\\\/papers\\\/dls-2024\\\/#listItem\",\"name\":\"dls-2024\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#organization\",\"name\":\"Deep Learning JP\",\"description\":\"Discover the Gradient\",\"url\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/author\\\/emma-nishioka\\\/#author\",\"url\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/author\\\/emma-nishioka\\\/\",\"name\":\"Emma Nishioka\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#authorImage\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7abaa1013c816fd68eb7dd5940eb1b27b8dc2bd9268c7a25e77488747bf6967e?s=96&d=mm&r=g\",\"width\":96,\"height\":96,\"caption\":\"Emma Nishioka\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#webpage\",\"url\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/\",\"name\":\"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP\",\"description\":\"(\\u65e5\\u672c\\u8a9e) \\u3010DL\\u8f2a\\u8aad\\u4f1a\\u3011MoE-LLaVA: Mixture of Experts for Large Vis\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/moe-llava-mixture-of-experts-for-largevision-language-models\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/author\\\/emma-nishioka\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/author\\\/emma-nishioka\\\/#author\"},\"datePublished\":\"2024-02-09T12:43:03+09:00\",\"dateModified\":\"2024-07-22T12:53:26+09:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/\",\"name\":\"Deep Learning JP\",\"description\":\"Discover the Gradient\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/deeplearning.jp\\\/en\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP","description":"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis","canonical_url":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":"&lt;!-- Google tag (gtag.js) --&gt;\n&lt;script async src=\"https:\/\/www.googletagmanager.com\/gtag\/js?id=G-S7YG337LDD\"&gt;&lt;\/script&gt;\n&lt;script&gt;\n  window.dataLayer = window.dataLayer || [];\n  function gtag(){dataLayer.push(arguments);}\n  gtag('js', new Date());\n\n  gtag('config', 'G-S7YG337LDD');\n&lt;\/script&gt;"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#article","name":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP","headline":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models","author":{"@id":"https:\/\/deeplearning.jp\/en\/author\/emma-nishioka\/#author"},"publisher":{"@id":"https:\/\/deeplearning.jp\/en\/#organization"},"datePublished":"2024-02-09T12:43:03+09:00","dateModified":"2024-07-22T12:53:26+09:00","inLanguage":"en-US","mainEntityOfPage":{"@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#webpage"},"isPartOf":{"@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#webpage"},"articleSection":"dls-2024,"},{"@type":"BreadcrumbList","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/#listItem","position":1,"name":"Home","item":"https:\/\/deeplearning.jp\/en\/","nextItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/#listItem","name":"seminar"}},{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/#listItem","position":2,"name":"seminar","item":"https:\/\/deeplearning.jp\/en\/category\/seminar\/","previousItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/#listItem","position":3,"item":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/","nextItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/#listItem","name":"dls-2024"},"previousItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/#listItem","name":"seminar"}},{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/#listItem","position":4,"name":"dls-2024","item":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/","nextItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#listItem","name":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models"}},{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#listItem","position":5,"name":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models","previousItem":{"@type":"ListItem","@id":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/#listItem","name":"dls-2024"}}]},{"@type":"Organization","@id":"https:\/\/deeplearning.jp\/en\/#organization","name":"Deep Learning JP","description":"Discover the Gradient","url":"https:\/\/deeplearning.jp\/en\/"},{"@type":"Person","@id":"https:\/\/deeplearning.jp\/en\/author\/emma-nishioka\/#author","url":"https:\/\/deeplearning.jp\/en\/author\/emma-nishioka\/","name":"Emma Nishioka","image":{"@type":"ImageObject","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#authorImage","url":"https:\/\/secure.gravatar.com\/avatar\/7abaa1013c816fd68eb7dd5940eb1b27b8dc2bd9268c7a25e77488747bf6967e?s=96&d=mm&r=g","width":96,"height":96,"caption":"Emma Nishioka"}},{"@type":"WebPage","@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#webpage","url":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/","name":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP","description":"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/deeplearning.jp\/en\/#website"},"breadcrumb":{"@id":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/#breadcrumblist"},"author":{"@id":"https:\/\/deeplearning.jp\/en\/author\/emma-nishioka\/#author"},"creator":{"@id":"https:\/\/deeplearning.jp\/en\/author\/emma-nishioka\/#author"},"datePublished":"2024-02-09T12:43:03+09:00","dateModified":"2024-07-22T12:53:26+09:00"},{"@type":"WebSite","@id":"https:\/\/deeplearning.jp\/en\/#website","url":"https:\/\/deeplearning.jp\/en\/","name":"Deep Learning JP","description":"Discover the Gradient","inLanguage":"en-US","publisher":{"@id":"https:\/\/deeplearning.jp\/en\/#organization"}}]},"og:locale":"en_US","og:site_name":"Deep Learning JP","og:type":"article","og:title":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP","og:description":"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis","og:url":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/","og:image":"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg","og:image:secure_url":"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg","og:image:width":450,"og:image:height":300,"article:published_time":"2024-02-09T03:43:03+00:00","article:modified_time":"2024-07-22T03:53:26+00:00","twitter:card":"summary","twitter:title":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models | Deep Learning JP","twitter:description":"(\u65e5\u672c\u8a9e) \u3010DL\u8f2a\u8aad\u4f1a\u3011MoE-LLaVA: Mixture of Experts for Large Vis","twitter:image":"https:\/\/deeplearning.jp\/wp-content\/uploads\/2018\/06\/img_DLapplied-1.jpg"},"aioseo_meta_data":{"post_id":"16330","title":null,"description":null,"keywords":[],"keyphrases":{"focus":{"keyphrase":"","score":0,"analysis":{"keyphraseInTitle":{"score":0,"maxScore":9,"error":1}}},"additional":[]},"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":"","og_custom_url":null,"og_article_section":null,"og_article_tags":[],"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"Article","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":"-1","robots_max_videopreview":"-1","robots_max_imagepreview":"large","priority":null,"frequency":"default","local_seo":null,"limit_modified_date":false,"created":"2024-02-09 03:42:13","updated":"2024-07-22 03:53:27","focus_keyword":null,"additional_keywords":null,"truseo_locale":null,"ai":null,"breadcrumb_settings":null,"seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/deeplearning.jp\/en\/\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/deeplearning.jp\/en\/category\/seminar\/\" title=\"seminar\">seminar<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/\" title=\"\"><\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/\" title=\"dls-2024\">dls-2024<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">\u00bb<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tMoE-LLaVA: Mixture of Experts for LargeVision-Language Models\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/deeplearning.jp\/en\/"},{"label":"seminar","link":"https:\/\/deeplearning.jp\/en\/category\/seminar\/"},{"label":"","link":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/"},{"label":"dls-2024","link":"https:\/\/deeplearning.jp\/en\/category\/seminar\/papers\/dls-2024\/"},{"label":"MoE-LLaVA: Mixture of Experts for LargeVision-Language Models","link":"https:\/\/deeplearning.jp\/en\/moe-llava-mixture-of-experts-for-largevision-language-models\/"}],"_links":{"self":[{"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/posts\/16330","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/users\/43"}],"replies":[{"embeddable":true,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/comments?post=16330"}],"version-history":[{"count":2,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/posts\/16330\/revisions"}],"predecessor-version":[{"id":16827,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/posts\/16330\/revisions\/16827"}],"wp:attachment":[{"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/media?parent=16330"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/categories?post=16330"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/deeplearning.jp\/en\/wp-json\/wp\/v2\/tags?post=16330"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}