[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-icml-2026-motion-attribution-motive":3,"news-related-36e9e98a-7d93-4e87-ad9e-a72af72a2c1c":33},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":20,"news_slug":26,"published_at":27,"created_at":28,"modified_at":29,"is_published":30,"publish_type":31,"image_url":13,"view_count":32},"36e9e98a-7d93-4e87-ad9e-a72af72a2c1c","ICML 2026 荣誉提名 Motive:首个『运动归因』框架,让视频生成学会挑运动片段","NVIDIA、MIT、Princeton 等联合团队在 ICML 2026 上以 Motive 拿下杰出论文荣誉提名。Motive 是首个面向视频生成模型的「运动归因」框架,基于光流掩码和梯度归因,只用 10% 数据就把 Wan2.1-T2V-1.3B 的 VBench Dynamic Degree 拉高 8.0 个点、Wan2.2-TI2V-5B 拉高 6.3 个点,17 人 850 次盲评胜率 74.1%。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.08828","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17],{"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},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",{"id":18,"name":19,"slug":19,"description":13,"color":13},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[21],{"id":22,"lang":23,"title":24,"summary":25,"content":13},"c605c15e-6784-419f-928f-79f5950acce3","en","Motive (ICML): the first motion attribution framework","A joint team from NVIDIA, MIT, Princeton, and others took an ICML 2026 Outstanding Paper Honorable Mention with Motive. Motive is the first \"motion attribution\" framework for video generation models, based on optical-flow masks and gradient attribution, and using only 10% of the data, it lifts Wan2.1-T2V-1.3B's VBench Dynamic Degree by 8.0 points, and Wan2.2-TI2V-5B by 6.3 points, with a 74.1% win rate in 850 blind evaluations from 17 human evaluators.","icml-2026-motion-attribution-motive","2026-07-07T08:30:00Z","2026-07-07T08:11:50.675357Z","2026-08-19T02:08:40.142862Z",true,"agent",91,{"items":34},[35,40,45,50,55,60],{"id":36,"title":37,"news_slug":38,"published_at":39},"79ed2e02-2fe4-43ca-a9b2-847740969424","HDR 把视频模型的多步推理硬拉出新手感:层级隐变量让经典规划任务成功率从 34% 跳到 60%","hdr-video-multi-step-planning","2026-07-18T12:00:00+00:00",{"id":41,"title":42,"news_slug":43,"published_at":44},"f884bd95-631b-4904-8e8d-a8db751f9314","MV-Forcing：用「4D 几何桥」打通「长 × 多视角」,单一扩散模型端到端跑出 4D 视频","mv-forcing-4d-bridge","2026-07-08T04:00:00+00:00",{"id":46,"title":47,"news_slug":48,"published_at":49},"0e44f256-e66e-495c-82e3-aae4dd5e2374","LiveEdit 把扩散视频编辑推到 12.66 FPS：清华让 AR 实时编辑走出 PPT","liveedit-ar-video-editing","2026-07-01T06:15:00+00:00",{"id":51,"title":52,"news_slug":53,"published_at":54},"62b2e6d9-4ac7-457c-a30c-548c713730ad","PhyCo：让视频生成模型「理解」物理世界","phyco-cvpr-2026-physics-video-controlnet-vlm-reward","2026-05-01T16:00:00+00:00",{"id":56,"title":57,"news_slug":58,"published_at":59},"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":61,"title":62,"news_slug":63,"published_at":64},"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"]