{"id":1407,"date":"2026-06-24T04:00:00","date_gmt":"2026-06-24T04:00:00","guid":{"rendered":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/"},"modified":"2026-06-24T06:59:52","modified_gmt":"2026-06-24T06:59:52","slug":"2412-08147","status":"publish","type":"post","link":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/","title":{"rendered":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning"},"content":{"rendered":"<p><br \/>\n<\/p>\n<div id=\"content-inner\">\n<div id=\"abs\">\n<div class=\"dateline\">\n  [Submitted on 11 Dec 2024 (v1), last revised 23 Jun 2026 (this version, v2)]<\/div>\n<p>View a PDF of the paper titled Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning, by Hugo Monz&#8217;on Maldonado and 4 different authors<\/p>\n<p>    View PDF<br \/>\n    HTML (experimental)<\/p>\n<blockquote class=\"abstract mathjax\"><p>\n            <span class=\"descriptor\">Summary:<\/span>Pareto fronts are helpful to search out good task-mixing methods for multitask finetuning, however they&#8217;re additionally expensive to compute. To scale back prices, latest works have used current mannequin merging strategies to assist prepare low-cost surrogate fashions to estimate the Pareto fronts. Nevertheless, no work has but thought-about designing new model-merging strategies to instantly, and provably, enhance the standard of Pareto fronts. Right here, we fill this hole by proposing a brand new Bayesian strategy known as Variational Mannequin Merging. On this strategy, current model-merging strategies are obtained as particular circumstances of &#8220;posterior-merging&#8221; when Gaussian posteriors are used and new model-merging methods might be derived through the use of non-Gaussian posteriors. Our most important theoretical result&#8217;s to point out that extra versatile posteriors essentially yield higher estimates of Pareto fronts. As an illustration, a Pareto entrance estimate obtained by merging full-Gaussian posteriors is anticipated to be higher than that obtained through the use of isotropic Gaussian posteriors. We validate the speculation via in depth empirical outcomes on imaginative and prescient and language transformers the place higher Gaussian households persistently yields higher or comparable Pareto fronts. Our work is a uncommon occasion the place Bayesian concepts are used to enhance Pareto evaluation.\n    <\/p><\/blockquote><\/div>\n<\/div>\n<div>\n<h2>Submission historical past<\/h2>\n<p> From: Hugo Monz\u00f3n Maldonado [view email]                  [v1]<br \/>\n        Wed, 11 Dec 2024 07:06:36 UTC (1,232 KB)<br \/>\n    [v2]<br \/>\n        Tue, 23 Jun 2026 16:19:45 UTC (2,662 KB)\n<\/p><\/div>\n<p><br \/>\n<br \/><a href=\"https:\/\/arxiv.org\/abs\/2412.08147\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>[Submitted on 11 Dec 2024 (v1), last revised 23 Jun 2026 (this version, v2)] View a PDF of the paper titled Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning, by Hugo Monz&#8217;on Maldonado and 4 different authors View PDF HTML (experimental) Summary:Pareto fronts are helpful to search out good task-mixing methods for multitask [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":1409,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","fifu_image_alt":"","jnews-multi-image_gallery":[],"jnews_single_post":[],"jnews_primary_category":[],"jnews_override_bookmark_settings":[],"jnews_social_meta":[],"jnews_override_counter":[],"footnotes":""},"categories":[2],"tags":[1871,1421,1870,1868,105,935,1869,1867],"class_list":["post-1407","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-research-breakthroughs","tag-estimation","tag-finetuning","tag-front","tag-merging","tag-model","tag-multitask","tag-pareto","tag-variational"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24<\/title>\n<meta name=\"description\" content=\"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24\" \/>\n<meta property=\"og:description\" content=\"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning\" \/>\n<meta property=\"og:url\" content=\"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/\" \/>\n<meta property=\"og:site_name\" content=\"Future News 24\" \/>\n<meta property=\"article:published_time\" content=\"2026-06-24T04:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-24T06:59:52+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png\" \/>\n<meta name=\"author\" content=\"Future News 24\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Future News 24\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\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\":\"Article\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/\"},\"author\":{\"name\":\"Future News 24\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\"},\"headline\":\"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning\",\"datePublished\":\"2026-06-24T04:00:00+00:00\",\"dateModified\":\"2026-06-24T06:59:52+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/\"},\"wordCount\":277,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/arxiv.org\\\/static\\\/browse\\\/0.3.4\\\/images\\\/arxiv-logo-fb.png\",\"keywords\":[\"Estimation\",\"FineTuning\",\"Front\",\"Merging\",\"Model\",\"Multitask\",\"Pareto\",\"Variational\"],\"articleSection\":[\"AI Research &amp; Breakthroughs\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/\",\"name\":\"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/arxiv.org\\\/static\\\/browse\\\/0.3.4\\\/images\\\/arxiv-logo-fb.png\",\"datePublished\":\"2026-06-24T04:00:00+00:00\",\"dateModified\":\"2026-06-24T06:59:52+00:00\",\"description\":\"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#primaryimage\",\"url\":\"http:\\\/\\\/arxiv.org\\\/static\\\/browse\\\/0.3.4\\\/images\\\/arxiv-logo-fb.png\",\"contentUrl\":\"http:\\\/\\\/arxiv.org\\\/static\\\/browse\\\/0.3.4\\\/images\\\/arxiv-logo-fb.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/24\\\/2412-08147\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/futurenews24.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"name\":\"Future News 24\",\"description\":\"The Smart Hub for AI and Next-Gen Innovation\",\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/futurenews24.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\",\"name\":\"Future News 24\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"contentUrl\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"width\":250,\"height\":250,\"caption\":\"Future News 24\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\",\"name\":\"Future News 24\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"caption\":\"Future News 24\"},\"sameAs\":[\"https:\\\/\\\/futurenews24.com\"],\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/author\\\/mridulpahuja20\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24","description":"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","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:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/","og_locale":"en_US","og_type":"article","og_title":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24","og_description":"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","og_url":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/","og_site_name":"Future News 24","article_published_time":"2026-06-24T04:00:00+00:00","article_modified_time":"2026-06-24T06:59:52+00:00","og_image":[{"url":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","type":"","width":"","height":""}],"author":"Future News 24","twitter_card":"summary_large_image","twitter_image":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","twitter_misc":{"Written by":"Future News 24","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#article","isPartOf":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/"},"author":{"name":"Future News 24","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83"},"headline":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning","datePublished":"2026-06-24T04:00:00+00:00","dateModified":"2026-06-24T06:59:52+00:00","mainEntityOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/"},"wordCount":277,"commentCount":0,"publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#primaryimage"},"thumbnailUrl":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","keywords":["Estimation","FineTuning","Front","Merging","Model","Multitask","Pareto","Variational"],"articleSection":["AI Research &amp; Breakthroughs"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/","url":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/","name":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning - Future News 24","isPartOf":{"@id":"https:\/\/futurenews24.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#primaryimage"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#primaryimage"},"thumbnailUrl":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","datePublished":"2026-06-24T04:00:00+00:00","dateModified":"2026-06-24T06:59:52+00:00","description":"Abstract page for arXiv paper 2412.08147: Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","breadcrumb":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#primaryimage","url":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png","contentUrl":"http:\/\/arxiv.org\/static\/browse\/0.3.4\/images\/arxiv-logo-fb.png"},{"@type":"BreadcrumbList","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/24\/2412-08147\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/futurenews24.com\/"},{"@type":"ListItem","position":2,"name":"[2412.08147] Variational Mannequin Merging for Pareto Entrance Estimation in Multitask Finetuning"}]},{"@type":"WebSite","@id":"https:\/\/futurenews24.com\/#website","url":"https:\/\/futurenews24.com\/","name":"Future News 24","description":"The Smart Hub for AI and Next-Gen Innovation","publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/futurenews24.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/futurenews24.com\/#organization","name":"Future News 24","url":"https:\/\/futurenews24.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/","url":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","contentUrl":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","width":250,"height":250,"caption":"Future News 24"},"image":{"@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83","name":"Future News 24","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","caption":"Future News 24"},"sameAs":["https:\/\/futurenews24.com"],"url":"https:\/\/futurenews24.com\/index.php\/author\/mridulpahuja20\/"}]}},"_links":{"self":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1407","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/comments?post=1407"}],"version-history":[{"count":1,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1407\/revisions"}],"predecessor-version":[{"id":1408,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1407\/revisions\/1408"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media\/1409"}],"wp:attachment":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media?parent=1407"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/categories?post=1407"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/tags?post=1407"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}