[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-sparse-attention":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"550a3d47-e632-4452-b9c2-c89caea4766e","sparse attention","sparse-attention",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"f15bbb27-837c-4841-9460-5c68d705e883","dashattention-differentiable-adaptive-sparse-attention-en","DashAttention makes sparse long-context attention differentiable","DashAttention uses adaptive sparse selection to keep hierarchical attention differentiable and improve long-context efficiency.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779171841715-ussc.png","en","2026-05-19T06:23:34.566629+00:00"]