[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-e4776508-8e3b-4eba-a804-ff4ee7e8a76d":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"e4776508-8e3b-4eba-a804-ff4ee7e8a76d","「Holo-World」用一张图控制相机、物体和天气：视频世界模型首次把\"环境状态\"做成独立控制轴","视频世界模型长期被一个隐含假设困住：想生成一段可控视频，要么给一段源视频，要么给一个完整 3D 场景。Holo-World 把这个二分法彻底拆掉——它用\"第一帧\"作为唯一锚点，把相机轨迹、物体运动和天气状态视为彼此正交的控制信号，从同一张图直接生成既能\"保住原世界\"也能\"切到目标天气\"的两类视频。\\n\\n论文的贡献分两层。数据层面，团队发布 HoloStateData，将散乱视频切成\"相机-物体-天气\"统一控制的样本，让监督信号本身就带解耦结构。模型层面，Unified Scene Adapter 显式把\"世界保持\"和\"天气迁移\"分到不同参数子空间，再用渲染背景、几何缓冲和物体控制稳住场景结构；天气部分交给 Scene-Weather Decomposed CFG 单独放大，避免传统 CFG 把整个条件都拉过去。量化实验显示，Holo-World 在天气生成任务上击败了需要\"先给视频\"的天气编辑基线。\\n\\n这条路径最大的意义在于：把\"可控性\"从堆叠控制模块的工程问题，变成参数空间可分解的建模问题。配合 first-frame 锚定，视频世界模型第一次可以像文生图那样，从单张图精细控制相机\u002F物体\u002F天气三轴，而不依赖昂贵的 3D 重建链路。对 AIGC 视频管线来说，这是从\"先建模再控制\"转向\"直接单帧控制\"的范式拐点。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.20083","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",{"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","2026-06-21T16:00:00Z","2026-06-21T16:15:12.250555Z","2026-06-21T16:15:12.250566Z",true,"agent",4]