{"id":2,"date":"2026-04-20T03:51:14","date_gmt":"2026-04-20T03:51:14","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/?page_id=2"},"modified":"2026-05-06T18:20:23","modified_gmt":"2026-05-06T18:20:23","slug":"sample-page","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/","title":{"rendered":"Related Work"},"content":{"rendered":"\n<p>One major challenge is lack of paired RGB-IR data.<\/p>\n\n\n\n<p class=\"has-text-align-left\"><strong>F-ViTA (Foundation Model Guided Visible-to-Infrared Translation)<\/strong><\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"942\" height=\"1024\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27-942x1024.png\" alt=\"\" class=\"wp-image-109\" style=\"aspect-ratio:0.9199402857752186;width:453px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27-942x1024.png 942w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27-276x300.png 276w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27-768x834.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27.png 1086w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n<\/div>\n\n\n<p class=\"has-text-align-left\">F-ViTA generates thermal (IR) images from RGB inputs using object-level and scene-level conditioning guided by foundation models. This allows models to learn realistic heat patterns and improves performance in settings where paired RGB-IR data is limited.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><strong>TherA (Thermal-Aware Visual-Language Prompting)<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"519\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12-1024x519.png\" alt=\"\" class=\"wp-image-50\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12-1024x519.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12-300x152.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12-768x389.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12-1536x778.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-12.png 1610w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<p>TherA enhances RGB-to-thermal translation by incorporating temperature-aware prompts, enabling more controllable and semantically meaningful thermal image generation. It improves how well generated IR images reflect real-world thermal cues, making them more useful for downstream tasks.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><strong>RARL (Reasoning-Aware Reinforcement Learning with LoRA)<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"559\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-13-1024x559.png\" alt=\"\" class=\"wp-image-51\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-13-1024x559.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-13-300x164.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-13-768x419.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-13.png 1408w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<p>RARL improves vision-language models by encouraging structured reasoning through reinforcement learning with multiple reward signals, including accuracy and reasoning quality. Combined with LoRA for efficient fine-tuning, it enables better generalization and transparent decision-making under limited data and compute constraints.<br><\/p>\n","protected":false},"excerpt":{"rendered":"<p>One major challenge is lack of paired RGB-IR data. F-ViTA (Foundation Model Guided Visible-to-Infrared Translation) F-ViTA generates thermal (IR) images from RGB inputs using object-level and scene-level conditioning guided by foundation models. This allows models to learn realistic heat patterns and improves performance in settings where paired RGB-IR data is limited. TherA (Thermal-Aware Visual-Language Prompting) &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Related Work&#8221;<\/span><\/a><\/p>\n","protected":false},"author":264,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-2","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge<\/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\/2026teamf21\/sample-page\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge\" \/>\n<meta property=\"og:description\" content=\"One major challenge is lack of paired RGB-IR data. F-ViTA (Foundation Model Guided Visible-to-Infrared Translation) F-ViTA generates thermal (IR) images from RGB inputs using object-level and scene-level conditioning guided by foundation models. This allows models to learn realistic heat patterns and improves performance in settings where paired RGB-IR data is limited. TherA (Thermal-Aware Visual-Language Prompting) &hellip; Continue reading &quot;Related Work&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/\" \/>\n<meta property=\"og:site_name\" content=\"Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-06T18:20:23+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1086\" \/>\n\t<meta property=\"og:image:height\" content=\"1180\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/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\\\/2026teamf21\\\/sample-page\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/\",\"name\":\"Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/05\\\/image-27-942x1024.png\",\"datePublished\":\"2026-04-20T03:51:14+00:00\",\"dateModified\":\"2026-05-06T18:20:23+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/05\\\/image-27.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/wp-content\\\/uploads\\\/sites\\\/163\\\/2026\\\/05\\\/image-27.png\",\"width\":1086,\"height\":1180},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/sample-page\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/\",\"name\":\"Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf21\\\/?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":"Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge","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\/2026teamf21\/sample-page\/","og_locale":"en_US","og_type":"article","og_title":"Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge","og_description":"One major challenge is lack of paired RGB-IR data. F-ViTA (Foundation Model Guided Visible-to-Infrared Translation) F-ViTA generates thermal (IR) images from RGB inputs using object-level and scene-level conditioning guided by foundation models. This allows models to learn realistic heat patterns and improves performance in settings where paired RGB-IR data is limited. TherA (Thermal-Aware Visual-Language Prompting) &hellip; Continue reading \"Related Work\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/","og_site_name":"Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge","article_modified_time":"2026-05-06T18:20:23+00:00","og_image":[{"width":1086,"height":1180,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27.png","type":"image\/png"}],"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\/2026teamf21\/sample-page\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/","name":"Related Work - Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27-942x1024.png","datePublished":"2026-04-20T03:51:14+00:00","dateModified":"2026-05-06T18:20:23+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-content\/uploads\/sites\/163\/2026\/05\/image-27.png","width":1086,"height":1180},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/sample-page\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/"},{"@type":"ListItem","position":2,"name":"Related Work"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/","name":"Multimodal Medical Triaging on UAV Data for DARPA Triage Challenge","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/?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\/2026teamf21\/wp-json\/wp\/v2\/pages\/2","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/users\/264"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/comments?post=2"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/pages\/2\/revisions"}],"predecessor-version":[{"id":110,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/pages\/2\/revisions\/110"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf21\/wp-json\/wp\/v2\/media?parent=2"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}