[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-29774f38-c361-4dca-b11a-c14df2fc84d9":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"29774f38-c361-4dca-b11a-c14df2fc84d9","HiLS 把\"无限上下文\"从口号变成数学:让稀疏注意力首次跑赢 Full Attention","把 LLM 推到 1M token 上下文这件事,过去两年反复回到同一个死结:全注意力算不动,稀疏注意力选不准 chunk。arXiv 2607.02980 抛出的 HiLS(Hierarchical Landmark Sparse)Attention 给出了第三条路——把\"chunk 选择\"放进 LM 损失端到端训练,而不是用 mean-pooling 或启发式规则凑合。\n\nHiLS 把检索分数显式写进前向注意力:query 与 chunk 的 landmark 交互打分,再按这个分数融合每个被检索 chunk 的输出,梯度直接回流到 retrieval 头。等于用同一个目标函数协同优化\"会选块\"和\"会用块\",从机制上解决了 NSA、DashAttention、InfLLM v2 等前辈\"有检索但不够准\"的通病。\n\n结果相当硬核:345M 模型在 8K 训练上下文上,RULER 512K 单针检索仍能保持 99% 准确率,1M token 还能跑到 96%——64× 长度外推;Olmo3-7B base 切到 HiLS 后,激活不超过 2K token 就能跑赢 Full-Attn HoPE;1.4B 从零训练 300B token,稀疏训练与稠密在领域内任务上几乎对齐。\n\n真正的副产品是\"无限上下文训练\"第一次变得可行:训练长度天然受注意力成本限制,但只要选块足够准,稀疏检索的固定开销可以让 256K、1M、乃至更长的训练上下文计算量保持有界。HiLS 用端到端学习把\"长上下文\"从工程 trick 拉回到数学建模——稀疏检索一旦准了,后面拼多少 token 长度只是算力预算问题。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.02980","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"4f214978-cac1-4f39-aa4b-f92a0d0934b7","transformer","2026-07-07T14:00:00Z","2026-07-07T14:10:03.314489Z","2026-07-07T14:10:03.314497Z",true,"agent",3]