{"id":7225,"date":"2025-09-30T04:03:01","date_gmt":"2025-09-30T04:03:01","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/09\/30\/interrupting-encoder-training-in-diffusion-models-enables-more-efficient-generative-ai\/"},"modified":"2025-09-30T04:03:01","modified_gmt":"2025-09-30T04:03:01","slug":"interrupting-encoder-training-in-diffusion-models-enables-more-efficient-generative-ai","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/09\/30\/interrupting-encoder-training-in-diffusion-models-enables-more-efficient-generative-ai\/","title":{"rendered":"Interrupting encoder training in diffusion models enables more efficient generative AI"},"content":{"rendered":"<p>    Interrupting encoder training in diffusion models enables more efficient generative AI<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>A new framework for generative diffusion models was developed by researchers at Science Tokyo, significantly improving generative AI models. The method reinterpreted Schr\u00f6dinger bridge models as variational autoencoders with infinitely many latent variables, reducing computational costs and preventing overfitting. By appropriately interrupting the training of the encoder, this approach enabled development of more efficient generative AI, with broad applicability beyond standard diffusion models.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><\/p>\n<p> \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/techxplore.com\/news\/2025-09-encoder-diffusion-enables-efficient-generative.html\">Go to techxplore<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Interrupting encoder training in diffusion models enables more efficient generative AI A new framework for generative diffusion models was developed by researchers at Science Tokyo, significantly improving generative AI models. The method reinterpreted Schr\u00f6dinger bridge models as variational autoencoders with infinitely many latent variables, reducing computational costs and preventing overfitting. By appropriately interrupting the training [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[54,45],"tags":[50],"class_list":["post-7225","post","type-post","status-publish","format-standard","hentry","category-computer-sciences","category-techxplore","tag-techxplore"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7225"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=7225"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7225\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=7225"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=7225"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=7225"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}