{"id":30,"date":"2025-05-06T04:20:12","date_gmt":"2025-05-06T04:20:12","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/?page_id=30"},"modified":"2025-05-08T05:17:12","modified_gmt":"2025-05-08T05:17:12","slug":"introduction","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","title":{"rendered":"Introduction"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

Before we dive into the project, take a look at the above figure and answer this question: Who are they?\u00a0<\/strong>Some faces may feel familiar, but naming them all is hard. Now, forget about names:\u00a0<\/span><\/span>Are they even the same individual?\u00a0<\/em>Most people would confidently say:\u00a0<\/span><\/span>No.<\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Now let’s jump into the second question of this series of shoes: How many distinct pairs of shoes do you see?<\/strong>
You might not recognize the exact Nike models, but by comparing subtle cues, like the number of logos, you\u2019ll notice:
Image 2 stands out.<\/strong>
It\u2019s a different pair.
This is what humans do effortlessly: visually link matching cues across images.<\/strong><\/p>\n\n\n\n

This ability to visually link matching cues<\/strong> across images requires no prior knowledge or labels<\/strong>\u2014just pure visual reasoning.<\/p>\n\n\n\n

As shown in the quizzes above, we can often identify whether two faces belong to the same person without knowing their names. Similarly, we can compare a photo of our favorite shoes to those on the shelf in a Footlocker store and quickly tell if they\u2019re the same model.<\/p>\n\n\n\n

What enables this is a simple yet powerful skill:
linking and matching visual cues across different images<\/strong> to judge identity and similarity.<\/p>\n\n\n\n

Recently, Large Language Model-based Vision-Language Models (VLMs) have demonstrated impressive world knowledge and expanded their capabilities from understanding single images to processing multiple images and even videos.<\/p>\n\n\n\n

However, increasing the number of images or context length alone does not ensure<\/strong> that these models can perform visual linking<\/strong>\u2014the ability to identify matching visual cues across different inputs.<\/p>\n\n\n\n

This remains an essential yet underexplored skill<\/strong> in multimodal reasoning, and one that current foundational models often struggle to master.<\/p>\n","protected":false},"excerpt":{"rendered":"

Before we dive into the project, take a look at the above figure and answer this question: Who are they?\u00a0Some faces may feel familiar, but naming them all is hard. Now, forget about names:\u00a0Are they even the same individual?\u00a0Most people would confidently say:\u00a0No. Now let’s jump into the second question of this series of shoes: … <\/p>\n

Continue reading “Introduction”<\/span><\/a><\/p>\n","protected":false},"author":232,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-30","page","type-page","status-publish","hentry"],"yoast_head":"\nIntroduction - LVLM Multi-image VQA Dehallucination<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Introduction - LVLM Multi-image VQA Dehallucination\" \/>\n<meta property=\"og:description\" content=\"Before we dive into the project, take a look at the above figure and answer this question: Who are they?\u00a0Some faces may feel familiar, but naming them all is hard. Now, forget about names:\u00a0Are they even the same individual?\u00a0Most people would confidently say:\u00a0No. Now let’s jump into the second question of this series of shoes: … Continue reading "Introduction"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/\" \/>\n<meta property=\"og:site_name\" content=\"LVLM Multi-image VQA Dehallucination\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-08T05:17:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-content\/uploads\/sites\/119\/2025\/05\/teaser1-1024x322.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/\",\"name\":\"Introduction - LVLM Multi-image VQA Dehallucination\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/wp-content\\\/uploads\\\/sites\\\/119\\\/2025\\\/05\\\/teaser1-1024x322.png\",\"datePublished\":\"2025-05-06T04:20:12+00:00\",\"dateModified\":\"2025-05-08T05:17:12+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/wp-content\\\/uploads\\\/sites\\\/119\\\/2025\\\/05\\\/teaser1.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/wp-content\\\/uploads\\\/sites\\\/119\\\/2025\\\/05\\\/teaser1.png\",\"width\":1938,\"height\":610},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Introduction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/\",\"name\":\"LVLM Multi-image VQA Dehallucination\",\"description\":\"Authors: Dongyu Yao, Keling Yao, Harry Chi; Advisor: Prof. Katia Sycara and Dr. Yaqi Xie\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team15\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Introduction - LVLM Multi-image VQA Dehallucination","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","og_locale":"en_US","og_type":"article","og_title":"Introduction - LVLM Multi-image VQA Dehallucination","og_description":"Before we dive into the project, take a look at the above figure and answer this question: Who are they?\u00a0Some faces may feel familiar, but naming them all is hard. Now, forget about names:\u00a0Are they even the same individual?\u00a0Most people would confidently say:\u00a0No. Now let’s jump into the second question of this series of shoes: … Continue reading \"Introduction\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","og_site_name":"LVLM Multi-image VQA Dehallucination","article_modified_time":"2025-05-08T05:17:12+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-content\/uploads\/sites\/119\/2025\/05\/teaser1-1024x322.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","name":"Introduction - LVLM Multi-image VQA Dehallucination","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-content\/uploads\/sites\/119\/2025\/05\/teaser1-1024x322.png","datePublished":"2025-05-06T04:20:12+00:00","dateModified":"2025-05-08T05:17:12+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-content\/uploads\/sites\/119\/2025\/05\/teaser1.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-content\/uploads\/sites\/119\/2025\/05\/teaser1.png","width":1938,"height":610},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/"},{"@type":"ListItem","position":2,"name":"Introduction"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/","name":"LVLM Multi-image VQA Dehallucination","description":"Authors: Dongyu Yao, Keling Yao, Harry Chi; Advisor: Prof. Katia Sycara and Dr. Yaqi Xie","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/pages\/30","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/users\/232"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/comments?post=30"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/pages\/30\/revisions"}],"predecessor-version":[{"id":75,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/pages\/30\/revisions\/75"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team15\/wp-json\/wp\/v2\/media?parent=30"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}