{"id":19,"date":"2024-05-12T16:47:14","date_gmt":"2024-05-12T16:47:14","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/?page_id=19"},"modified":"2024-05-12T16:48:45","modified_gmt":"2024-05-12T16:48:45","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/","title":{"rendered":"RELATED WORK"},"content":{"rendered":"\n
    \n
  1. Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation<\/strong><\/li>\n<\/ol>\n\n\n\n

    \u00b7 A pioneer text-to-image benchmark Involving human preferences<\/p>\n\n\n\n

    \u00b7 Limitations: excessive noise and lack of compositional information<\/p>\n\n\n\n

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

    2. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation<\/strong><\/p>\n\n\n\n

    \u00b7 Rich compositional information considered for text-to-image generation.<\/p>\n\n\n\n

    \u00b7 VQA formula employed for text-to-visual evaluation, yet lacks generalization.<\/p>\n\n\n\n

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

    3. When and Why Vision-Language Models Behave Like Bags-Of-Words, and What to Do About It?<\/strong><\/p>\n\n\n\n

    \u00b7 Critical compositional knowledge, including \u201cOrder,\u201d introduced for VLM evaluation<\/p>\n\n\n\n

    \u00b7 Limitations: not informative enough, questions easily solved without visual information<\/p>\n\n\n\n

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

    4. TIFA: Accurate and Interpretable Text-to-Image<\/strong> Faithfulness Evaluation with Question Answering<\/strong><\/p>\n\n\n\n

    \u00b7 Advanced faithfulness evaluation for text-to-visual generation with VQA models<\/p>\n\n\n\n

    \u00b7 Question filtering makes it non-end-to-end and challenging to use for rewarding fine-tuning in generative models.<\/p>\n\n\n

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

    5. Towards a Better Metric for Text-to-Video Generation<\/strong><\/p>\n\n\n\n

    \u00b7 Transfer alignment evaluation from text-to-image to text-to-video generation.<\/p>\n\n\n\n

    \u00b7 Accuracy calculation remains at post-decoder levels, neglecting the knowledge contained in logits.<\/p>\n\n\n

    \n
    \"\"<\/figure>\n<\/div>","protected":false},"excerpt":{"rendered":"

    \u00b7 A pioneer text-to-image benchmark Involving human preferences \u00b7 Limitations: excessive noise and lack of compositional information 2. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation \u00b7 Rich compositional information considered for text-to-image generation. \u00b7 VQA formula employed for text-to-visual evaluation, yet lacks generalization. 3. When and Why Vision-Language Models Behave Like Bags-Of-Words, and What to … <\/p>\n

    Continue reading “RELATED WORK”<\/span><\/a><\/p>\n","protected":false},"author":205,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-19","page","type-page","status-publish","hentry"],"yoast_head":"\nRELATED WORK - Alignment for Vision-Language Foundation Models<\/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\/2024team8\/related-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"RELATED WORK - Alignment for Vision-Language Foundation Models\" \/>\n<meta property=\"og:description\" content=\"\u00b7 A pioneer text-to-image benchmark Involving human preferences \u00b7 Limitations: excessive noise and lack of compositional information 2. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation \u00b7 Rich compositional information considered for text-to-image generation. \u00b7 VQA formula employed for text-to-visual evaluation, yet lacks generalization. 3. When and Why Vision-Language Models Behave Like Bags-Of-Words, and What to … Continue reading "RELATED WORK"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Alignment for Vision-Language Foundation Models\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-12T16:48:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/lh7-us.googleusercontent.com\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048\" \/>\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\\\/2024team8\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/\",\"name\":\"RELATED WORK - Alignment for Vision-Language Foundation Models\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048\",\"datePublished\":\"2024-05-12T16:47:14+00:00\",\"dateModified\":\"2024-05-12T16:48:45+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048\",\"contentUrl\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"RELATED WORK\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/\",\"name\":\"Alignment for Vision-Language Foundation Models\",\"description\":\"Students: Yixin Fei, Kewen Wu, Pengliang Ji | Advisors: Zhiqiu Lin, Deva Ramanan (Carnegie Mellon University, Robotics Institute)\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/?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 - Alignment for Vision-Language Foundation Models","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\/2024team8\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"RELATED WORK - Alignment for Vision-Language Foundation Models","og_description":"\u00b7 A pioneer text-to-image benchmark Involving human preferences \u00b7 Limitations: excessive noise and lack of compositional information 2. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation \u00b7 Rich compositional information considered for text-to-image generation. \u00b7 VQA formula employed for text-to-visual evaluation, yet lacks generalization. 3. When and Why Vision-Language Models Behave Like Bags-Of-Words, and What to … Continue reading \"RELATED WORK\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/","og_site_name":"Alignment for Vision-Language Foundation Models","article_modified_time":"2024-05-12T16:48:45+00:00","og_image":[{"url":"https:\/\/lh7-us.googleusercontent.com\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048","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\/2024team8\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/","name":"RELATED WORK - Alignment for Vision-Language Foundation Models","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/lh7-us.googleusercontent.com\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048","datePublished":"2024-05-12T16:47:14+00:00","dateModified":"2024-05-12T16:48:45+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/#primaryimage","url":"https:\/\/lh7-us.googleusercontent.com\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048","contentUrl":"https:\/\/lh7-us.googleusercontent.com\/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/"},{"@type":"ListItem","position":2,"name":"RELATED WORK"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/","name":"Alignment for Vision-Language Foundation Models","description":"Students: Yixin Fei, Kewen Wu, Pengliang Ji | Advisors: Zhiqiu Lin, Deva Ramanan (Carnegie Mellon University, Robotics Institute)","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/?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\/2024team8\/wp-json\/wp\/v2\/pages\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/users\/205"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/comments?post=19"}],"version-history":[{"count":3,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages\/19\/revisions"}],"predecessor-version":[{"id":22,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages\/19\/revisions\/22"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/media?parent=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}