[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-flashblock-cuts-attention-cost-in-long-context-diffusion-models":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},4170,"flashblock-cuts-attention-cost-in-long-context-diffusion-models","FlashBlock Cuts Attention Cost in Long-Context Diffusion Models","A new caching mechanism reuses stable attention outputs across diffusion steps, boosting token throughput by up to 1.44x without degrading output quality.","Researchers have found a way to make long-context diffusion models significantly faster by skipping attention work they were already repeating.\n\nThe paper introduces FlashBlock, a technique that targets a specific inefficiency in block diffusion — a popular inference method used in diffusion language models and video generators. In block diffusion, the model processes content in chunks and caches key-value pairs to avoid recomputing everything from scratch. The problem: as context grows, attention over that cache gets recomputed at every diffusion step anyway. FlashBlock's insight is that attention outputs from tokens *outside* the current block stay nearly constant across steps, while attention *within* the block changes meaningfully. By caching and reusing the stable external attention outputs, the system cuts redundant computation without touching the underlying diffusion process.\n\nThe gains are concrete: up to 1.44x higher token throughput and up to 1.6x faster attention time, with what the authors describe as negligible quality loss. The technique also stacks with sparse attention methods — rather than competing with existing efficiency tricks, it acts as a complementary layer, recovering accuracy that aggressive sparsification would otherwise sacrifice.\n\nDiffusion-based text and video generation has been gaining ground as an alternative to autoregressive models, partly on the promise of parallelism and speed. FlashBlock addresses a bottleneck that grows worse at exactly the scales — long videos, extended documents — where diffusion is most appealing. Whether the \"negligible\" quality caveat holds up outside controlled benchmarks is the question practitioners will want answered before shipping this.","[\"ai\",\"diffusion-models\",\"inference\",\"research\"]","2026-07-07T04:00:00.000Z","2026-07-07T18:56:40.119Z","2026-07-07T18:56:43.117Z","published",null,[],"ai",[24,26,27,28],"diffusion-models","inference","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05305",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]