{"id":41137,"date":"2025-08-12T10:28:00","date_gmt":"2025-08-12T02:28:00","guid":{"rendered":"https:\/\/www.1ai.net\/?p=41137"},"modified":"2025-08-12T10:28:00","modified_gmt":"2025-08-12T02:28:00","slug":"ai-%e7%94%9f%e6%88%90%e6%b8%b8%e6%88%8f%ef%bc%8c%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4%e5%8f%91%e5%b8%83%e5%b9%b6%e5%bc%80%e6%ba%90-matrix-game-2-0%e3%80%81matrix-3d-%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/41137.html","title":{"rendered":"AI-generated games, Kunlun World Wide releases and open-sources Matrix-Game 2.0, Matrix-3D models"},"content":{"rendered":"<p>August 12 News.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4\" title=\"[Sees articles with [Konlen] tags]\" target=\"_blank\" >Kunlun Wanwei<\/a> SkyWork AI Technology Release Week was launched on August 11, with one model released every day for five consecutive days, covering core multimodal AI scenarios.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-41138\" title=\"496b5cf4j00t0v05e00ptd000u000gwp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/08\/496b5cf4j00t0v05e00ptd000u000gwp.jpg\" alt=\"496b5cf4j00t0v05e00ptd000u000gwp\" width=\"1080\" height=\"608\" \/><\/p>\n<p>Today, Kunlun World Wide brings the upgraded version of the Matrix-Game interactive world model in the Matrix series of self-developed world models --- the Matrix-Game interactive world model.<strong>\"Matrix-Game 2.0\".<\/strong>, claiming to be a world model that realizes interactive real-time long sequence generation in generic scenarios.<\/p>\n<p>and in order to promote the field of interactive world modeling.<strong>\"Matrix-Game 2.0\" Full Open Source<\/strong>, which is claimed to be the industry's first open source solution for real-time long sequence interactive generation of world models on generic scenarios.<\/p>\n<p><strong>\"Matrix-Game 2.0\".<\/strong>It is claimed to be a \"quantum leap\" in real-time generation and long sequence capabilities. Compared to the previous version, version 2.0 focuses more on low-latency, high-frame-rate long sequence interactive performance.<strong>Stable generation of continuous video content at 25 FPS in a wide range of complex scenarios, with scalable generation durations down to the minute level<\/strong>, dramatically improving coherence and utility.<\/p>\n<p>While the reasoning speed is significantly increased, the model still maintains a \"precise understanding\" of the physical laws and scene semantics, and supports users to freely explore, manipulate, and build real-time virtual environments with clear structure, rich details, and reasonable rules through simple commands.<\/p>\n<p>Kunlun Wanwei also open-sources\u00a0<strong>Matrix-3D Large Model<\/strong>The result is a high-quality, trajectory-consistent panoramic video that starts from a single image and directly restores the roamable 3D space, benchmarking against Feifei Li's WorldLabs generation for a larger range of explorable spaces.<\/p>\n<p>Matrix-3D consists of the following core components:<\/p>\n<ul>\n<li><strong>Trajectory-guided panoramic video generation module:<\/strong>Using scene mesh renderings as conditional inputs, a video diffusion model is trained to generate panoramic videos that conform to a given camera trajectory. It improves the consistency of the generated video in terms of spatial structure and mitigates occlusion errors and image artifacts.<\/li>\n<li><strong>Dual-path selectable panoramic 3D reconstruction module:<\/strong>Optimization Path: Optimize the generated video with super-segmentation and 3DGS to obtain high-quality 3D structures. Feedforward network path: based on Transformer direct regression, fast prediction of 3D geometric attributes from Latent features of the generated video, realizing efficient reconstruction.<\/li>\n<li><strong>Matrix-Pano dataset:<\/strong>Large-scale, high-quality synthetic dataset containing 116K static panoramic video sequences with camera tracks, depth maps, and text annotations.<\/li>\n<\/ul>\n<p>1AI attaches the open source addresses of the two models as follows:<\/p>\n<p>https:\/\/github.com\/SkyworkAI\/Matrix-Game<\/p>\n<p>https:\/\/github.com\/SkyworkAI\/Matrix-3D<\/p>","protected":false},"excerpt":{"rendered":"<p>August 12, 2011 - Kunlun World Wide's SkyWork AI Technology Release Week was launched on August 11, with one model released every day for five consecutive days, covering the core multi-modal AI scenarios. Today, Kunlun brings the upgraded version of Matrix-Game interactive world model in Matrix series of self-developed world model - \"Matrix-Game 2.0\", which is claimed to be a world model that realizes interactive real-time long sequence generation in general scenarios. In order to promote the development of interactive world modeling, \"Matrix-Game 2.0\" is fully open source, which is claimed to be the industry's first open source solution to realize real-time long sequence interactive world model generation on general scenarios. \"Matrix-Ga<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[862,1050],"collection":[],"class_list":["post-41137","post","type-post","status-publish","format-standard","hentry","category-news","tag-862","tag-1050"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/41137","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=41137"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/41137\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=41137"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=41137"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=41137"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=41137"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}