[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-video-generation":3},{"tag":4,"articles":11,"peer_article_count":101},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"9d786a9c-c6f0-4c37-9f0a-2aab262eabce","video generation","video-generation",4,"影片生成正在從「會動」走向「可控、可解釋」：研究重點包括時間一致性、速度與節奏控制、相機與物件運動分離，以及主動／被動動作建模，讓生成結果更接近真實世界的因果關係與使用者意圖。","Video generation is shifting from making clips that merely move to models that can be controlled and reasoned about. Current work focuses on temporal consistency, playback speed, camera-object motion separation, and active vs. passive actions to better match user intent and real-world causality.",[12,21,29,36,44,52,59,66,73,80,87,94],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"9bd27b93-b6f8-448d-af75-22ba07d8c1c3","grok-imagine-1-5-turns-prompts-into-720p-video-en","Grok Imagine 1.5 turns prompts into 720p video","I break down Grok Imagine Video 1.5 and give you a copy-ready prompt workflow for fast 720p video generation.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782475418949-cvva.png","en","2026-06-26T12:03:03.32881+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"9736a608-9aac-42b8-912a-94ceb2944a84","openai-sora-hardware-enterprise-video-en","OpenAI’s Sora hardware targets enterprise video","OpenAI’s Sora enterprise hardware brings local AI video generation to studios, agencies, and firms that need speed and privacy.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782382685120-i4ci.png","2026-06-25T10:17:39.504946+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":17,"image_url":34,"cover_image":34,"language":19,"created_at":35},"7da5424f-1ff8-483a-80ed-7091c5b0454b","crun-ai-gemini-omni-chat-video-editing-en","Crun AI turns Gemini Omni into chat video editing","Crun AI now exposes Gemini Omni so you can create and edit videos by chatting, with docs, credits, and usage tracking built in.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780733910991-ji5m.png","2026-06-06T08:18:00.680201+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":41,"image_url":42,"cover_image":42,"language":19,"created_at":43},"9cfac677-c848-40f6-8beb-6b68acd0cf60","4-reasons-gemini-users-hit-caps-fast-en","4 reasons Gemini users hit caps so fast","4 reasons Gemini users are hitting usage caps fast, plus what Google says about the new compute-based limit system.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780371165682-4xt8.png","2026-06-02T03:32:19.407752+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":49,"image_url":50,"cover_image":50,"language":19,"created_at":51},"b48efbc5-ad8d-4b54-80bb-110e5c7d9a70","lumos-nexus-frequency-bridging-video-models-en","Lumos-Nexus bridges reasoning and video quality","Lumos-Nexus separates training from inference to improve video quality without sacrificing reasoning-driven generation.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780293783880-yq7p.png","2026-06-01T06:02:36.330284+00:00",{"id":53,"slug":54,"title":55,"summary":56,"category":49,"image_url":57,"cover_image":57,"language":19,"created_at":58},"66608799-65b1-4143-afc1-d1457cdd696a","refdecoder-reference-conditioned-video-decoder-en","RefDecoder adds reference conditioning to video decoders","RefDecoder feeds reference image detail into video decoders, improving consistency and reconstruction without extra fine-tuning.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778912631938-tra3.png","2026-05-16T06:23:34.829247+00:00",{"id":60,"slug":61,"title":62,"summary":63,"category":49,"image_url":64,"cover_image":64,"language":19,"created_at":65},"d60602fc-ed44-4c5e-8aa1-b0285672b8ba","entitybench-long-range-video-consistency-en","EntityBench Tackles Long-Range Video Consistency","EntityBench measures whether video models keep characters, objects, and locations consistent across long, multi-shot sequences.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778911850469-mgcy.png","2026-05-16T06:10:29.577019+00:00",{"id":67,"slug":68,"title":69,"summary":70,"category":49,"image_url":71,"cover_image":71,"language":19,"created_at":72},"70ef52bd-60f4-42ce-8ef8-9344e65d96d8","actcam-joint-camera-motion-control-en","ActCam adds joint camera and motion control","ActCam is a zero-shot way to steer both actor motion and camera path in video generation without training a new model.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778220661882-aj3y.png","2026-05-08T06:10:39.382021+00:00",{"id":74,"slug":75,"title":76,"summary":77,"category":17,"image_url":78,"cover_image":78,"language":19,"created_at":79},"52b5b347-44cb-4fc0-a04a-6c6ed4557e5f","how-to-migrate-from-sora-2-in-2026-en","How to Migrate from Sora 2 in 2026","Migrate Sora 2 video workflows to new models before OpenAI’s shutdown deadlines.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778137244620-k6m4.png","2026-05-07T07:00:30.019537+00:00",{"id":81,"slug":82,"title":83,"summary":84,"category":49,"image_url":85,"cover_image":85,"language":19,"created_at":86},"d14b7cf3-fc52-4889-9d8f-ba08deb677b8","teaching-video-models-understand-time-en","Teaching Video Models to Understand Time","A self-supervised way to detect speed changes, estimate playback speed, and generate or sharpen videos at controlled timing.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777010642456-9rzz.png","2026-04-24T06:03:37.245074+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":49,"image_url":92,"cover_image":92,"language":19,"created_at":93},"0625f19d-6f12-4d22-bab3-8b2e8b89d84f","moright-motion-control-causality-en","MoRight tackles motion control and causality","MoRight separates camera and object motion, and models active vs. passive actions so video generation can react more plausibly to user input.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775715012291-9ibo.png","2026-04-09T06:09:32.139302+00:00",{"id":95,"slug":96,"title":97,"summary":98,"category":41,"image_url":99,"cover_image":99,"language":19,"created_at":100},"677cc705-258e-4459-ba27-e44a987d3325","sora-shutdown-ai-vendor-risk-en","Inside Sora's Shutdown and AI Vendor Risk","Sora peaked near 1 million users, then fell below 500,000 while burning about $1 million a day. The unit economics broke.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775198579935-wyfb.png","2026-04-03T06:42:29.348454+00:00",8]