{"id":241456,"date":"2026-07-24T00:07:47","date_gmt":"2026-07-24T05:07:47","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2026\/07\/novel-method-lets-multimodal-ai-update-knowledge-without-losing-earlier-information"},"modified":"2026-07-24T00:07:47","modified_gmt":"2026-07-24T05:07:47","slug":"novel-method-lets-multimodal-ai-update-knowledge-without-losing-earlier-information","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2026\/07\/novel-method-lets-multimodal-ai-update-knowledge-without-losing-earlier-information","title":{"rendered":"Novel method lets multimodal AI update knowledge without losing earlier information"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/novel-method-lets-multimodal-ai-update-knowledge-without-losing-earlier-information2.jpg\"><\/a><\/p>\n<p>Korean researchers have developed a core technology that allows multimodal artificial intelligence (AI) to reliably retain existing knowledge while repeatedly learning new information.<\/p>\n<p>Electronics and Telecommunications Research Institute (ETRI) announced that the \u201cContinual and Compositional Knowledge Editing Technology (MemEIC),\u201d jointly developed by a research team led by Director Lim Soo Jong of the Language Intelligence Research Section with Pohang University of Science and Technology and Sungkyunkwan University, was presented at NeurIPS 2025, an AI conference held in San Diego late last year.<\/p>\n<p>The work is <a href=\"https:\/\/arxiv.org\/abs\/2510.25798\" target=\"_blank\">published<\/a> on the <i>arXiv<\/i> preprint server.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Korean researchers have developed a core technology that allows multimodal artificial intelligence (AI) to reliably retain existing knowledge while repeatedly learning new information. Electronics and Telecommunications Research Institute (ETRI) announced that the \u201cContinual and Compositional Knowledge Editing Technology (MemEIC),\u201d jointly developed by a research team led by Director Lim Soo Jong of the Language Intelligence [\u2026]<\/p>\n","protected":false},"author":662,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-241456","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/241456","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/662"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=241456"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/241456\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=241456"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=241456"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=241456"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}