[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-nvidia-flex-forcing-ar-bidir-video":3,"news-related-58764a46-a635-4f79-86c6-eefff0dea639":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},"58764a46-a635-4f79-86c6-eefff0dea639","Flex-Forcing：NVIDIA 用 chunk 机制把 AR 与双向视频扩散塞进同一模型","NVIDIA GenAIR 团队 7 月 3 日发布 Flex-Forcing,提出沿时间轴与去噪步数双重定义的 chunk 机制,把双向扩散与自回归视频生成统一在同一个模型中;chunk 间双向、chunk 内自回归,粒度随显存预算伸缩,支持任意顺序重排,在多套视频 benchmark 上同时拿下更长视频稳定性、更高视觉质量和更快推理。项目页:research.nvidia.com\u002Flabs\u002Fgenair\u002Fflex-forcing。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.03509","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model",{"id":18,"name":19,"slug":19,"description":13,"color":13},"8dac812d-3839-4abe-a855-5f56ec9515fd","nvidia",{"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},"2fc823c9-641d-4abe-b2aa-8871cc6c7df2","en","Flex-Forcing: AR and bidirectional diffusion in one model","NVIDIA's GenAIR team on July 3 released Flex-Forcing, proposing a chunk mechanism defined along both the time axis and the denoising step count, unifying bidirectional diffusion and autoregressive video generation in the same model; bidirectional between chunks, autoregressive within chunks, granularity scales with the memory budget, supports arbitrary order rearrangement, simultaneously capturing longer video stability, higher visual quality, and faster inference on multiple video benchmarks. Project page: research.nvidia.com\u002Flabs\u002Fgenair\u002Fflex-forcing.","nvidia-flex-forcing-ar-bidir-video","2026-07-08T18:24:00Z","2026-07-08T18:23:57.488178Z","2026-08-19T02:08:40.142862Z",true,"agent",98,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"75d2f385-00ef-4074-80bf-ee47ba05a4a4","NVIDIA × HF：Diffusers 微调上 H100，Wan 2.2\u002FFLUX.2 打通","nvidia-huggingface-diffusers-h100","2026-07-17T14:00:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"8058b748-25c6-4863-917e-46e363773d07","WanToFight 把视频扩散压成 30FPS 实时游戏引擎:多玩家格斗首跑通","wantofight-real-time-game","2026-07-15T16:05:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"f4c705fd-47c9-481a-807f-8001820070f8","InfinityEdit:三注意力轻量适配器,把视频编辑推进无界流时代","infinityedit-infinite-video-editing-adapter","2026-08-25T13:00:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"18d2aa73-7244-4b10-b611-46475e17327e","ForgeWM开源:一步去噪72FPS的可玩世界模型,8张卡复现全流程","forgewm-few-step-playable-world-model","2026-08-24T21:10:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"2874a2e5-beae-4627-8f6f-a34cf2cc8d7a","一段随手拍视频直出4D人体:4DAnyone用RCP+TCR破解多视角一致性,代码权重全开源","4danyone-monocular-video-4d-human","2026-08-20T17:59:53+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"5612d186-46ee-4509-9a93-94045ba004ae","LTX-2.5 开放权重视频模型:4K 反而在 Fast 端点,EXR 色彩管线也焊进去了","ltx-2-5-open-weights-video","2026-08-18T15:20:00+00:00"]