{"id":30931,"date":"2026-11-18T09:05:22","date_gmt":"2026-11-18T08:05:22","guid":{"rendered":"https:\/\/saarland-informatics-campus.de\/?post_type=sic_news&#038;p=30931"},"modified":"2026-11-19T12:56:21","modified_gmt":"2026-11-19T11:56:21","slug":"when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand","status":"publish","type":"sic_news","link":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/","title":{"rendered":"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand"},"content":{"rendered":"<p><strong>Modern AI models deliver impressive results in image recognition, image description, or image analysis\u2014but how they arrive at these results often remains unclear. A research team at the Max Planck Institute for Informatics has now developed a new approach called the Language-aligned Concept Foundation Model for Vision (CFM), which adds an explanatory layer to powerful AI models for vision: The system explains its results in terms people can understand, and shows the image regions on which those results are based. The work was presented as a spotlight paper in September 2026 at one of the world\u2019s leading conferences in Visual Computing.<\/strong><\/p>\n<p>Foundation models are AI models trained on enormous amounts of data that can subsequently be adapted to perform a wide range of tasks\u2014much like an operating system that supports a variety of programs. One type is the language-aligned vision foundation model (VLM), which is trained on millions of image-text pairs, enabling it to connect images with language. Today, they are used in a wide range of applications, from image recognition and image search to image generation, and in combination with large language models.<\/p>\n<p>However, these models have a critical weakness: Humans cannot easily understand how they arrive at their results. For example, a model might correctly identify a malignant mole in a medical image\u2014but until now, it has been difficult to determine why the model identified it and it and what it actually &#8220;saw&#8221; in the image. This lack of transparency is considered a major obstacle to the widespread adoption of AI-based systems, especially in safety-critical or sensitive areas such as medicine. &#8220;Only if we understand what a model&#8217;s decision is based on can we check whether it is correct for the right reasons, or find out why it failed when it made a mistake,&#8221; says Dr. Jonas Fischer, head of the research group Explainable Machine Learning at the Max Planck Institute for Informatics in Saarbr\u00fccken.<\/p>\n<p>This is where the research team consisting of Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, and Jonas Fischer comes in\u2014with a new modelling approach, the Language-aligned Concept Foundation Model for Vision (CFM). First, an image is divided into small sections called patches. A small network is specifically trained to translate the numerical values (vector data) represented in the model into clearly defined concepts and assings them concise, human-readable labels. Because each patch is analyzed individually, the system can determine where each concept appears in the image. By identifying concepts that occur together in the same regions, the method can also establish broader and narrower categories\u2014for example, that a &#8220;sailboat&#8221; is a specific type of &#8220;ship\/boat.&#8221;<\/p>\n<div id=\"attachment_30934\" style=\"width: 610px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-30934\" class=\"wp-image-30934 size-full\" src=\"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_MPII9718_edit_c6bda524a0.jpg\" alt=\"PhD Student Kai Wittenmayer, First Author of the paper. Foto: MPI-INF\/ Philipp Zapf-Schramm\" width=\"600\" height=\"450\" \/><p id=\"caption-attachment-30934\" class=\"wp-caption-text\">PhD Student Kai Wittenmayer, First Author of the paper. Foto: MPI-INF\/ Philipp Zapf-Schramm<\/p><\/div>\n<p>Unlike previous approaches that simply list the concepts a model appears to recognize in an image, CFM explains its decisions by pinpointing where the individual concepts appear in the image.<\/p>\n<p>&#8220;CFM can not only reveal which concepts a model recognizes in an image, but also selectively influence them. In image description tasks, for example, individual concepts can be suppressed so that certain image contents are no longer mentioned in the image description, while others continue to be described,&#8221; explains doctoral student Kai Wittenmayer, the paper\u2019s first author.<\/p>\n<p>The Saarbr\u00fccken researcher\u2019s proof-of-concept study opens up far-reaching application possibilities: Language-aligned vision foundation models often provide the foundation that enables large language models (LLMs) to process images and text simultaneously. The new Concept Foundation Model makes it possible to break down and explain image components in a way that humans can understand. This makes it possible to idenitfy and correct unreliable or erroneous model behavior early on, without having to retrain a model from scratch. This could improve efficiency by eliminating time-consuming and resource-intensive training.<\/p>\n<p>CFM is the first foundation model that provides explanations for a variety of downstream tasks based on understandable concepts: Including image classification, image description, and image segmentation. Previous approaches to explainability have mostly been limited to image classification. The additional explanatory layer has only a minimal impact on performance. In tests, CFM achieved performance levels nearly identical to those of the underlying, opaque models across the tasks mentioned above.<\/p>\n<p>&#8220;CFM could be useful wherever AI decisions need to be explainable. For example, it could eventually be used in medicine, to ensure that a melanoma was identified based on diagnostic features, rather than the presence of hospital gloves in the image,&#8221; explains Bernt Schiele, Director of the Computer Vision and Machine Learning department at the Max Planck Institute for Informatics. Next, the researchers plan to combine their concept representation with large language and image models, for example for use in visual question-answering systems.<\/p>\n<p>The research was presented as a spotlight paper at the European Conference on Computer Vision (ECCV) in September 2026, one of the world\u2019s leading conferences in visual computing. The 2026 conference was held in Malm\u00f6, Sweden.<\/p>\n<p><strong>Original publication:<\/strong><br \/>\nKai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer: \u201eCFM: Language-aligned Concept Foundation Model for Vision&#8221;. European Conference on Computer Vision (ECCV), Malm\u00f6, 2026. <a class=\"link-external\" href=\"https:\/\/eccv.ecva.net\/virtual\/2026\/spotlight\/6025\" target=\"_blank\" rel=\"noopener noreferrer\">https:\/\/eccv.ecva.net\/virtual\/2026\/spotlight\/6025<\/a><\/p>\n<p><strong>Scientific contact:<\/strong><br \/>\nDr. Jonas Fischer<br \/>\nResearch Group Leader, Max Planck Institute for Informatics<br \/>\nEmail: <a href=\"mailto:jonas.fischer@mpi-inf.mpg.de\">jonas.fischer@mpi-inf.mpg.de<\/a><\/p>\n<p><strong>Editor:<br \/>\n<\/strong>Philipp Zapf-Schramm<br \/>\nJoint Administration<br \/>\nMax Planck Institute for Informatics<br \/>\nMax Planck Institute for Software Systems<br \/>\n<span style=\"background-color: transparent;\">Tel: +49 681 9325 4509<br \/>\nEmail: <\/span><a href=\"mailto:pzs@mpi-klsb.mpg.de\"><span style=\"background-color: transparent;\">pzs@mpi-klsb.mpg.de<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Modern AI models deliver impressive results in image recognition, image description, or image analysis&mdash;but how they arrive at these results often remains unclear. A research team at the Max Planck Institute for Informatics has now developed a new approach called the Language-aligned Concept Foundation Model for Vision (CFM), which adds an explanatory layer to powerful [&hellip;]<\/p>\n","protected":false},"featured_media":30929,"menu_order":0,"template":"","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":""},"sic_news-types":[110,56,59],"class_list":["post-30931","sic_news","type-sic_news","status-publish","has-post-thumbnail","hentry","sic_news-types-feedreader-en","sic_news-types-mpi-inf-en","sic_news-types-press-release-en"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus<\/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:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus\" \/>\n<meta property=\"og:description\" content=\"Modern AI models deliver impressive results in image recognition, image description, or image analysis&mdash;but how they arrive at these results often remains unclear. A research team at the Max Planck Institute for Informatics has now developed a new approach called the Language-aligned Concept Foundation Model for Vision (CFM), which adds an explanatory layer to powerful [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/\" \/>\n<meta property=\"og:site_name\" content=\"Saarland Informatics Campus\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/sic.informatik.saarland\/\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-19T11:56:21+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1082\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\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=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/\",\"url\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/\",\"name\":\"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/wp-content\\\/uploads\\\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg\",\"datePublished\":\"2026-11-18T08:05:22+00:00\",\"dateModified\":\"2026-11-19T11:56:21+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/#primaryimage\",\"url\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/wp-content\\\/uploads\\\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg\",\"contentUrl\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/wp-content\\\/uploads\\\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg\",\"width\":1920,\"height\":1082},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"News\",\"item\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/piece-of-news\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/\",\"name\":\"Saarland Informatics Campus\",\"description\":\"in Saarbr\u00fccken, Germany\",\"publisher\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#organization\",\"name\":\"Saarland Informatics Campus\",\"url\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/wp-content\\\/uploads\\\/SIC_logo_1453x343.png\",\"contentUrl\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/wp-content\\\/uploads\\\/SIC_logo_1453x343.png\",\"width\":1453,\"height\":343,\"caption\":\"Saarland Informatics Campus\"},\"image\":{\"@id\":\"https:\\\/\\\/saarland-informatics-campus.de\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/sic.informatik.saarland\\\/\",\"https:\\\/\\\/bsky.app\\\/profile\\\/saarland-informatics-campus.de\",\"https:\\\/\\\/www.instagram.com\\\/saarland_informatics_campus\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCaDDK5m9CGCzE4xhZTFC6cA\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/saarland-informatics-campus\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus","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:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/","og_locale":"en_US","og_type":"article","og_title":"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus","og_description":"Modern AI models deliver impressive results in image recognition, image description, or image analysis&mdash;but how they arrive at these results often remains unclear. A research team at the Max Planck Institute for Informatics has now developed a new approach called the Language-aligned Concept Foundation Model for Vision (CFM), which adds an explanatory layer to powerful [&hellip;]","og_url":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/","og_site_name":"Saarland Informatics Campus","article_publisher":"https:\/\/www.facebook.com\/sic.informatik.saarland\/","article_modified_time":"2026-11-19T11:56:21+00:00","og_image":[{"width":1920,"height":1082,"url":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/","url":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/","name":"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand - Saarland Informatics Campus","isPartOf":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/#primaryimage"},"image":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/#primaryimage"},"thumbnailUrl":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg","datePublished":"2026-11-18T08:05:22+00:00","dateModified":"2026-11-19T11:56:21+00:00","breadcrumb":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/#primaryimage","url":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg","contentUrl":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/csm_DSCF5436_edit_1_0d749d321d-e1795088555879.jpg","width":1920,"height":1082},{"@type":"BreadcrumbList","@id":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/when-ai-reveals-what-it-sees-saarbruecken-researchers-make-ai-for-vision-easier-to-understand\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/saarland-informatics-campus.de\/en\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/saarland-informatics-campus.de\/en\/piece-of-news\/"},{"@type":"ListItem","position":3,"name":"When AI reveals what it sees: Saarbr\u00fccken Researchers Make AI for Vision Easier to Understand"}]},{"@type":"WebSite","@id":"https:\/\/saarland-informatics-campus.de\/en\/#website","url":"https:\/\/saarland-informatics-campus.de\/en\/","name":"Saarland Informatics Campus","description":"in Saarbr\u00fccken, Germany","publisher":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/saarland-informatics-campus.de\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/saarland-informatics-campus.de\/en\/#organization","name":"Saarland Informatics Campus","url":"https:\/\/saarland-informatics-campus.de\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/saarland-informatics-campus.de\/en\/#\/schema\/logo\/image\/","url":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/SIC_logo_1453x343.png","contentUrl":"https:\/\/saarland-informatics-campus.de\/wp-content\/uploads\/SIC_logo_1453x343.png","width":1453,"height":343,"caption":"Saarland Informatics Campus"},"image":{"@id":"https:\/\/saarland-informatics-campus.de\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/sic.informatik.saarland\/","https:\/\/bsky.app\/profile\/saarland-informatics-campus.de","https:\/\/www.instagram.com\/saarland_informatics_campus\/","https:\/\/www.youtube.com\/channel\/UCaDDK5m9CGCzE4xhZTFC6cA","https:\/\/www.linkedin.com\/company\/saarland-informatics-campus"]}]}},"_links":{"self":[{"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/sic_news\/30931","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/sic_news"}],"about":[{"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/types\/sic_news"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/media\/30929"}],"wp:attachment":[{"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/media?parent=30931"}],"wp:term":[{"taxonomy":"sic_news-types","embeddable":true,"href":"https:\/\/saarland-informatics-campus.de\/en\/wp-json\/wp\/v2\/sic_news-types?post=30931"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}