{"id":8012,"date":"2026-01-05T02:51:00","date_gmt":"2026-01-04T17:51:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=8012"},"modified":"2026-01-04T07:55:53","modified_gmt":"2026-01-03T22:55:53","slug":"yume-1-5-a-text-controlled-interactive-world-generation-model","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=8012","title":{"rendered":"Yume-1.5: A Text-Controlled Interactive World Generation Model\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Yume-1.5: A Text-Controlled Interactive World Generation Model\u00a0<\/strong>[78.9]<br>Method\u306f\u3001\u5358\u4e00\u306e\u753b\u50cf\u3084\u30c6\u30ad\u30b9\u30c8\u30d7\u30ed\u30f3\u30d7\u30c8\u304b\u3089\u73fe\u5b9f\u7684\u3067\u30a4\u30f3\u30bf\u30e9\u30af\u30c6\u30a3\u30d6\u3067\u9023\u7d9a\u7684\u306a\u4e16\u754c\u3092\u751f\u6210\u3059\u308b\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u305f\u65b0\u3057\u3044\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b\u3002 \u30e1\u30bd\u30c3\u30c9\u306f\u3001\u30ad\u30fc\u30dc\u30fc\u30c9\u30d9\u30fc\u30b9\u306e\u751f\u6210\u4e16\u754c\u3092\u63a2\u7d22\u3059\u308b\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u614e\u91cd\u306b\u8a2d\u8a08\u3057\u3001\u3053\u308c\u3092\u5b9f\u73fe\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2512.22096v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2512.22096v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 26 Dec 2025 17:52:49 GMT)<\/li>\n\n\n\n<li>\u300cwe present Yume1.5, an interactive world generation model that enables infinite video generation from a single input image through autoregressive synthesis while supporting intuitive keyboard-based camera control.\u300d\u3001\u300cThe key innovations of Yume1.5 include: (1) a joint temporal-spatial-channel modeling approach that enables efficient long video generation while maintaining temporal coherence; (2) an acceleration method that mitigates error accumulation during inference; and (3) text-controlled world event generation capability achieved through careful architectural design and mixed-dataset training.\u300d\u3068\u306e\u3053\u3068\u3002\u52d5\u753b\u751f\u6210\u7cfb\u3001world model\u306b\u3064\u306a\u304c\u308b\u7814\u7a76\u3002\u5922\u3001\u4e16\u754c\uff08<a href=\"https:\/\/github.com\/Lixsp11\/sekai-codebase\">GitHub &#8211; Lixsp11\/sekai-codebase: [NeurIPS 2025] The official repository of &#8220;Sekai: A Video Dataset towards World Exploration&#8221;<\/a>\uff09\u3068\u30cd\u30fc\u30df\u30f3\u30b0\u3082\u9762\u767d\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/stdstu12\/YUME\">GitHub &#8211; stdstu12\/YUME: The official code of Yume<\/a>\u3001\u30e2\u30c7\u30eb\u306f<a href=\"https:\/\/huggingface.co\/stdstu123\/Yume-5B-720P\">stdstu123\/Yume-5B-720P \u00b7 Hugging Face<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[449],"class_list":["post-8012","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-world-model"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8012","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8012"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8012\/revisions"}],"predecessor-version":[{"id":8013,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8012\/revisions\/8013"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8012"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8012"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8012"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}