[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-motionstream-snu-adobe-29fps-real-time-video":3,"news-related-b70fac6f-aedc-41ee-8c84-0fc47e8d7930":31},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":24,"published_at":25,"created_at":26,"modified_at":27,"is_published":28,"publish_type":29,"image_url":13,"view_count":30},"b70fac6f-aedc-41ee-8c84-0fc47e8d7930","MotionStream：实时视频生成领域的交互式运动控制突破","Seoul National University、Adobe Research等机构联合推出MotionStream，支持交互式运动控制的实时流式视频生成系统。该系统在单块NVIDIA H100 GPU上实现29 FPS流式生成，延迟仅0.4秒。通过双向教师模型到因果学生模型的蒸馏技术，结合滑动窗口因果注意力和KV缓存滚动，解决了长时间视频生成的三大挑战：领域桥接、质量维持和计算效率。这一突破标志着视频生成技术从离线处理向实时交互的重大转变。","https:\u002F\u002Fjoonghyuk.com\u002Fmotionstream-web\u002Findex.html","c5570fa2-6b28-415f-9c91-006dd19f5327",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model",{"id":21,"name":22,"slug":22,"description":13,"color":13},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[],"motionstream-snu-adobe-29fps-real-time-video","2026-04-24T16:06:00Z","2026-04-24T16:06:58.926224Z","2026-08-19T02:08:40.142862Z",true,"agent",131,{"items":32},[33,38,43,48,53,58],{"id":34,"title":35,"news_slug":36,"published_at":37},"c463258a-094c-4217-8130-eef2bfacf78c","Xmax X2.0 把实时交互视频模型端侧化:逐帧自回归 + 消费级显卡跑 960p@24fps","xmax-x2-realtime-video","2026-07-16T08:00:00+00:00",{"id":39,"title":40,"news_slug":41,"published_at":42},"aebb8a81-713a-40b7-84dd-03213a6a808c","Mistral Robostral Navigate:8B 视觉语言模型只靠单目 RGB 在 R2R-CE 反超多传感器基线","mistral-robostral-navigate-8b","2026-07-09T14:15:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"bce04851-f4a1-410c-b543-d08e45eb4a37","Grok 4.5 私测启动：1.5T V9 + Cursor 数据，宣称对标 Opus 4.6","grok-4-5-1-5t-v9-cursor-beta","2026-06-29T10:01:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"d653e1b1-d348-48e3-9a84-62f9ece9418c","Sakana Fugu 用「指挥家模型」对齐 Fable 5：多智能体编排能不能成为 LLM 下一站？","sakana-fugu-conductor-model-orchestration","2026-06-23T20:00:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"cec093b3-47fe-490f-b0d7-57c07ba19758","Wan-Streamer v0.1：单模型端到端 550ms 实时交互","wan-streamer-v0-1-550ms-realtime","2026-06-23T18:01:03+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"43644653-55a5-40e6-b48c-dd9a548b7311","可灵 3.0 Turbo 落地：把视频生成拆成「快速预览 + 影院成片」两段式工作流","kling-3-0-turbo-two-stage-workflow","2026-06-22T00:04:00+00:00"]