--- title: How To Train Multimodal LLMs To Understand And Interact... description: The post discusses several multimodal Large Language Models (LLMs) and their capabilities, including KosMos-2, Shikra, GPT-4V, and Gemini. canonical: https://daily.dev/posts/how-to-train-multimodal-llms-to-understand-and-interact-with-text-image-video-and-audio-model-and-umgbdauxs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How To Train Multimodal LLMs To Understand And Interact With Text, Image, Video And Audio: Model And Methods（Continued） | daily.dev og:description: The post discusses several multimodal Large Language Models (LLMs) and their capabilities, including KosMos-2, Shikra, GPT-4V, and Gemini. og:url: https://daily.dev/posts/how-to-train-multimodal-llms-to-understand-and-interact-with-text-image-video-and-audio-model-and-umgbdauxs og:image: https://api.daily.dev/og/posts/umgbdAuxS.png og:image:alt: How To Train Multimodal LLMs To Understand And Interact With Text, Image, Video And Audio: Model And Methods（Continued） og:image:width: 1200 og:image:height: 630 og:locale: en --- [AI in Plain English](https://daily.dev/sources/aiplainenglish) [Read post](https://api.daily.dev/r/umgbdAuxS) # [How To Train Multimodal LLMs To Understand And Interact With Text, Image, Video And Audio: Model And Methods（Continued）](https://api.daily.dev/r/umgbdAuxS "Go to post") The post discusses several multimodal Large Language Models (LLMs) and their capabilities, including KosMos-2, Shikra, GPT-4V, and Gemini. [#llm](/tags/llm "Check all #llm posts") Apr 02, 2024•5m read time•From [ai.plainenglish.io](https://api.daily.dev/r/umgbdAuxS "ai.plainenglish.io") [](https://api.daily.dev/r/umgbdAuxS "Go to post") Table of contents [Kosmos-2](https://api.daily.dev/r/umgbdAuxS?a=0d55 "Kosmos-2")[Shikra](https://api.daily.dev/r/umgbdAuxS?a=8d85 "Shikra")[GPT4V](https://api.daily.dev/r/umgbdAuxS?a=36a2 "GPT4V")[Gemini](https://api.daily.dev/r/umgbdAuxS?a=ad30 "Gemini") 40 Impressions4 Upvotes Comment Bookmark Copy Share your thoughtsPost [](https://daily.dev/sources/aiplainenglish) [AI in Plain English](https://daily.dev/sources/aiplainenglish "https://daily.dev/sources/aiplainenglish") 1.9K Followers • 628 Upvotes #### Would you recommend this post? Copy link WhatsApp Facebook X New Squad Copy linkShare with your friends 4 ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How To Train Multimodal LLMs To Understand And Interact With Text, Image, Video And Audio: Model And Methods（Continued）","url":"https://daily.dev/posts/how-to-train-multimodal-llms-to-understand-and-interact-with-text-image-video-and-audio-model-and-umgbdauxs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-train-multimodal-llms-to-understand-and-interact-with-text-image-video-and-audio-model-and-umgbdauxs"},"datePublished":"2024-04-02T10:48:31.063Z","dateModified":"2024-05-09T08:43:33.910Z","description":"The post discusses several multimodal Large Language Models (LLMs) and their capabilities, including KosMos-2, Shikra, GPT-4V, and Gemini.","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/aa2754e809566645bd48cb70544c2d60?_a=AQAEufR","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/aa2754e809566645bd48cb70544c2d60?_a=AQAEufR","isAccessibleForFree":true,"articleSection":"AI in Plain English","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI in Plain English","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/8a17667bb9684f35ae94c89e2d61e7eb","url":"https://daily.dev/sources/aiplainenglish"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-train-multimodal-llms-to-understand-and-interact-with-text-image-video-and-audio-model-and-umgbdauxs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":4},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI in Plain English","item":"https://daily.dev/sources/aiplainenglish"},{"@type":"ListItem","position":3,"name":"How To Train Multimodal LLMs To Understand And Interact With Text, Image, Video And Audio: Model And Methods（Continued）"}]} ```