[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-kunlun-waic-matrix-3-5":3,"news-related-f0ea091f-d030-4a32-827a-ae21c1b61c8f":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"f0ea091f-d030-4a32-827a-ae21c1b61c8f","昆仑万维 WAIC 大会将一次性放出四款全模态模型：Matrix-3.5 把\"状态-动作\"塞进一套参数","WAIC 2026 第三天(7月19日),昆仑万维旗下 Skywork 将在同一场论坛一次性发布 Matrix-3.5 世界模型、SkyReels v4.5 视频大模型、Mureka v9.5 音乐大模型、Riemann-1.0 机器人模型,分别对应\"视、听、动、境\"四个维度,构成\"全模态+具身智能\"战略的完整拼图。旗舰 Matrix-3.5 的关键创新是把\"下一帧状态生成\"与\"动作生成\"合并训练——5B 参数、720P@40FPS 实时交互,彻底重构长时记忆架构。同期,Skywork 已积累 500 万+ 高质量视频切片、1 万+ 训练小时、1200+ 游戏场景数,构建 UE5 自主探索+跨游戏自动化+开放视频挖掘三条自动化数据管线,把物理因果标注压到工程级。该发布标志世界模型从\"预测下一帧\"升级为\"状态-动作联合理解与生成\",为后续机器人控制、自动驾驶仿真与通用智能体训练铺底。","https:\u002F\u002Fwww.qbitai.com\u002F2026\u002F06\u002F435520.html","ab05b869-89f1-4253-828c-0e498b25e49c",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":18,"name":19,"slug":19,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":21,"name":22,"slug":22,"description":13,"color":13},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"be520a2d-db79-4514-abd4-591c24002bff","en","Kunlun releases four omni-modal models; Matrix-3.5 unifies them","On day three of WAIC 2026 (July 19), Kunlun Wanwei's Skywork is set to release four models in a single forum session: the Matrix-3.5 world model, the SkyReels v4.5 video model, the Mureka v9.5 music model, and the Riemann-1.0 robot model — corresponding to the four dimensions of \"vision, sound, motion, environment\", and together forming the complete mosaic of its \"full-modality + embodied intelligence\" strategy. The headline Matrix-3.5's key innovation is the joint training of \"next-frame state generation\" with \"action generation\" — 5B parameters, 720P@40FPS real-time interaction, and a fully re-architected long-term memory structure. In parallel, Skywork has accumulated 5M+ high-quality video clips, 10K+ training hours, and 1,200+ game scenarios, with three automated data pipelines (UE5 autonomous exploration + cross-game automation + open-source video mining) that compress physics-causal annotation to engineering-grade quality. This release marks the upgrade of the world model from \"predict the next frame\" to \"joint state-action understanding and generation\", laying the foundation for subsequent robot control, autonomous driving simulation, and general-agent training.","kunlun-waic-matrix-3-5","2026-07-17T12:08:00Z","2026-07-17T12:10:45.879878Z","2026-08-19T02:08:40.142862Z",true,"agent",399,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"6ed14a36-a62a-43e8-949a-cf9df4405d98","Seedance 2.5 把视频生成送进 B 端:30 张参考图、API 上火山方舟、徐工小鹏首批接入","seedance-2-5-enterprise-api-b2b","2026-08-01T04:30:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"2fbfa6c5-3bf5-4279-a353-6324396b2d36","字节 Seedance 2.5 把单段视频拉到 30 秒：视频生成终于\"能用\"了？","bytedance-seedance-2-5-30s-video-model","2026-07-31T06:00:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"b4214f43-353e-42e3-b48e-92dd4fc64290","京东开源 EchoWM 全模态世界模型:720p 音画同步,能跟着你走","jd-echowm-omnimodal-world-model","2026-08-25T23:10:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"7ef479ae-66af-463a-802f-07a84ade93b1","商汤开源 SenseNova-U1.5-8B：原生多模态通吃生成编辑，短板全写进模型卡","sensenova-u1-5-8b-open-source-multimodal","2026-08-25T19:30:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"6f9e9f94-9dcc-4c6c-b254-6c5d0fe8ed37","京东开源 JoyAI-Video-Edit:16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-realtime-diffusion","2026-08-10T00:00:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"bcdc10bc-2f08-4c39-8ffa-e7e34041c112","京东开源 JoyAI-Video-Edit:用 16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-real-time-streaming","2026-08-05T03:00:00+00:00"]