{"id":225,"date":"2024-08-20T11:10:42","date_gmt":"2024-08-20T11:10:42","guid":{"rendered":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/"},"modified":"2024-08-20T11:10:42","modified_gmt":"2024-08-20T11:10:42","slug":"koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus","status":"publish","type":"post","link":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/","title":{"rendered":"KOALA (Architecture d’Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l’Optimisation de la R\u00e9daction de Contenus"},"content":{"rendered":"

<\/p>\n

\u00c0 mesure que les mod\u00e8les de langage (LLMs) deviennent plus complexes, leur processus d’inf\u00e9rence se r\u00e9v\u00e8le co\u00fbteux en termes de calcul et de temps. Des applications comme la traduction en temps r\u00e9el ou les syst\u00e8mes de dialogue n\u00e9cessitent des r\u00e9ponses rapides, mais l’inf\u00e9rence lente augmente les co\u00fbts op\u00e9rationnels.<\/p>\n

Des chercheurs de l’Universit\u00e9 de Technologie de Dalian, en Chine, ont relev\u00e9 le d\u00e9fi de la latence \u00e9lev\u00e9e des LLMs due \u00e0 la nature s\u00e9quentielle de leur d\u00e9codage autor\u00e9gressif. Bien que des m\u00e9thodes comme le d\u00e9codage sp\u00e9culatif aient \u00e9t\u00e9 propos\u00e9es, leur potentiel n’est pas pleinement exploit\u00e9 \u00e0 cause de la t\u00eate de brouillon monocouche utilis\u00e9e qui a des performances limit\u00e9es.<\/p>\n

Ils introduisent KOALA (K-layer Optimized Adversarial Learning Architecture), qui optimise la t\u00eate de brouillon en la transformant en architecture multicouche et en ajoutant un apprentissage adversarial, permettant d’am\u00e9liorer la pr\u00e9cision des pr\u00e9dictions. KOALA a \u00e9t\u00e9 \u00e9valu\u00e9 avec succ\u00e8s, d\u00e9montrant une augmentation de vitesse de 10,57%-14,09% dans diff\u00e9rents mod\u00e8les Vicuna.<\/p>\n

En conclusion, KOALA repr\u00e9sente une avanc\u00e9e importante pour am\u00e9liorer l’efficacit\u00e9 des LLMs gr\u00e2ce \u00e0 sa capacit\u00e9 \u00e0 acc\u00e9l\u00e9rer le processus d’inf\u00e9rence.<\/p>\n","protected":false},"excerpt":{"rendered":"

\u00c0 mesure que les mod\u00e8les de langage (LLMs) deviennent plus complexes, leur processus d’inf\u00e9rence se r\u00e9v\u00e8le co\u00fbteux en termes de calcul et de temps. Des applications comme la traduction en temps r\u00e9el ou les syst\u00e8mes de dialogue n\u00e9cessitent des r\u00e9ponses rapides, mais l’inf\u00e9rence lente augmente les co\u00fbts op\u00e9rationnels. Des chercheurs de l’Universit\u00e9 de Technologie de […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-225","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"\nKOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES<\/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:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"KOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES\" \/>\n<meta property=\"og:description\" content=\"\u00c0 mesure que les mod\u00e8les de langage (LLMs) deviennent plus complexes, leur processus d’inf\u00e9rence se r\u00e9v\u00e8le co\u00fbteux en termes de calcul et de temps. Des applications comme la traduction en temps r\u00e9el ou les syst\u00e8mes de dialogue n\u00e9cessitent des r\u00e9ponses rapides, mais l’inf\u00e9rence lente augmente les co\u00fbts op\u00e9rationnels. Des chercheurs de l’Universit\u00e9 de Technologie de […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/\" \/>\n<meta property=\"og:site_name\" content=\"IA & TECHNOLOGIES\" \/>\n<meta property=\"article:published_time\" content=\"2024-08-20T11:10:42+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D\" \/>\n<meta name=\"author\" content=\"m\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"m\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/\",\"url\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/\",\"name\":\"KOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES\",\"isPartOf\":{\"@id\":\"https:\/\/www.asm15.fr\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D\",\"datePublished\":\"2024-08-20T11:10:42+00:00\",\"author\":{\"@id\":\"https:\/\/www.asm15.fr\/#\/schema\/person\/9e2a0039267955de05a7ce4282a905e6\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage\",\"url\":\"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D\",\"contentUrl\":\"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\/\/www.asm15.fr\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"KOALA (Architecture d’Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l’Optimisation de la R\u00e9daction de Contenus\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.asm15.fr\/#website\",\"url\":\"https:\/\/www.asm15.fr\/\",\"name\":\"IA & TECHNOLOGIES\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.asm15.fr\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.asm15.fr\/#\/schema\/person\/9e2a0039267955de05a7ce4282a905e6\",\"name\":\"m\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/www.asm15.fr\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/6fe5cecb08501f51d81efa38bdd65daa775b9224f6dc9617c8615be766310093?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/6fe5cecb08501f51d81efa38bdd65daa775b9224f6dc9617c8615be766310093?s=96&d=mm&r=g\",\"caption\":\"m\"},\"sameAs\":[\"https:\/\/www.asm15.fr\"],\"url\":\"https:\/\/www.asm15.fr\/index.php\/author\/m\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"KOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES","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:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/","og_locale":"fr_FR","og_type":"article","og_title":"KOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES","og_description":"\u00c0 mesure que les mod\u00e8les de langage (LLMs) deviennent plus complexes, leur processus d’inf\u00e9rence se r\u00e9v\u00e8le co\u00fbteux en termes de calcul et de temps. Des applications comme la traduction en temps r\u00e9el ou les syst\u00e8mes de dialogue n\u00e9cessitent des r\u00e9ponses rapides, mais l’inf\u00e9rence lente augmente les co\u00fbts op\u00e9rationnels. Des chercheurs de l’Universit\u00e9 de Technologie de […]","og_url":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/","og_site_name":"IA & TECHNOLOGIES","article_published_time":"2024-08-20T11:10:42+00:00","og_image":[{"url":"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D","type":"","width":"","height":""}],"author":"m","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"m","Dur\u00e9e de lecture estim\u00e9e":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/","url":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/","name":"KOALA (Architecture d'Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l'Optimisation de la R\u00e9daction de Contenus - IA & TECHNOLOGIES","isPartOf":{"@id":"https:\/\/www.asm15.fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage"},"image":{"@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage"},"thumbnailUrl":"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D","datePublished":"2024-08-20T11:10:42+00:00","author":{"@id":"https:\/\/www.asm15.fr\/#\/schema\/person\/9e2a0039267955de05a7ce4282a905e6"},"breadcrumb":{"@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#primaryimage","url":"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D","contentUrl":"https:\/\/oaidalleapiprodscus.blob.core.windows.net\/private\/org-PXteLUy4B6mslwRon6h7ri9z\/user-0jfma6aPNvZyLXZUbw4CmvZG\/img-vbVRNzPkFz5xgFDiNI2Q5kH3.png?st=2024-08-20T10%3A10%3A41Z&se=2024-08-20T12%3A10%3A41Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image\/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-08-19T23%3A20%3A23Z&ske=2024-08-20T23%3A20%3A23Z&sks=b&skv=2024-08-04&sig=foNXyohGGrH1pZous6Fptqe8ostoPbK4BhxR6ZPy59k%3D"},{"@type":"BreadcrumbList","@id":"https:\/\/www.asm15.fr\/index.php\/2024\/08\/20\/koala-architecture-dapprentissage-adversarial-optimisee-par-couches-une-technique-orthogonale-pour-loptimisation-de-la-redaction-de-contenus\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/www.asm15.fr\/"},{"@type":"ListItem","position":2,"name":"KOALA (Architecture d’Apprentissage Adversarial Optimis\u00e9e par Couches): Une Technique Orthogonale pour l’Optimisation de la R\u00e9daction de Contenus"}]},{"@type":"WebSite","@id":"https:\/\/www.asm15.fr\/#website","url":"https:\/\/www.asm15.fr\/","name":"IA & TECHNOLOGIES","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.asm15.fr\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Person","@id":"https:\/\/www.asm15.fr\/#\/schema\/person\/9e2a0039267955de05a7ce4282a905e6","name":"m","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.asm15.fr\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/6fe5cecb08501f51d81efa38bdd65daa775b9224f6dc9617c8615be766310093?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/6fe5cecb08501f51d81efa38bdd65daa775b9224f6dc9617c8615be766310093?s=96&d=mm&r=g","caption":"m"},"sameAs":["https:\/\/www.asm15.fr"],"url":"https:\/\/www.asm15.fr\/index.php\/author\/m\/"}]}},"_links":{"self":[{"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/posts\/225","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/comments?post=225"}],"version-history":[{"count":0,"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/posts\/225\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/media?parent=225"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/categories?post=225"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.asm15.fr\/index.php\/wp-json\/wp\/v2\/tags?post=225"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}