[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-speed-up-ai-video-generation-with-smarter-attention":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},8613,"researchers-speed-up-ai-video-generation-with-smarter-attention","Researchers Speed Up AI Video Generation With Smarter Attention","A new method called PSA speeds up AI video generation up to 1.57x by exploiting repeating stripe patterns in model attention.","AI video generation just got a speed boost from a smarter way of deciding which pixels actually need to talk to each other.\n\nResearchers built a technique called Parameterized Stripe Attention, or PSA, that speeds up Diffusion Transformers, the models behind tools like HunyuanVideo and Wan 2.1. The slowdown in video generation comes from full spatio-temporal attention: every frame's pixels comparing themselves against every other frame's pixels, an expensive process. The team found this attention naturally forms repeating diagonal stripe patterns across time and space, then built a single CUDA kernel that exploits that structure instead of guessing at sparse patterns on the fly. A training-free search algorithm tunes how aggressively to trim each attention head without exceeding a set error tolerance.\n\nThis matters because earlier sparse-attention methods forced a trade-off. Fixed masks ran fast but couldn't adapt; flexible masks adapted but ran slow. PSA claims to dodge that trade-off, delivering up to 1.57x speedup over FlashAttention-3 on HunyuanVideo and 1.37x on Wan 2.1, with what the researchers call \"acceptable\" quality loss.\n\n\"Acceptable\" is doing a lot of work in that sentence, and this year every efficiency paper benchmarks against FlashAttention-3. The real test is whether video model builders actually bolt this kernel on, not whether it beats a baseline in a paper.","[\"ai\",\"video-generation\",\"diffusion-models\",\"gpu-optimization\"]","2026-09-30T04:00:00.000Z","2026-09-30T14:58:29.386Z","2026-09-30T14:58:36.011Z","published",null,[],"ai",[24,26,27,28],"video-generation","diffusion-models","gpu-optimization",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.37001",0,{"sections":35},[36,39,43,47,52,57,62,67,72,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5135,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",788,{"name":44,"slug":45,"count":46,"latest_published_at":18},"Policy","policy",417,{"name":48,"slug":49,"count":50,"latest_published_at":51},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":53,"slug":54,"count":55,"latest_published_at":56},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":58,"slug":59,"count":60,"latest_published_at":61},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":18},"Dev Tools","dev-tools",90,{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]