[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-c1ee21bd-4b59-418a-9b77-e46c790a8978":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},"c1ee21bd-4b59-418a-9b77-e46c790a8978","InfoKV 把 KV 缓存压缩推过「只看注意力」的临界点：用信息熵帮推理模型跑得更长","InfoKV (arXiv 2606.26875) 用信息熵替代纯注意力评分，把 KV 缓存压缩推过「近距影响」临界点：针对 DeepSeek-R1 等长链推理模型，把 token 级预测不确定性与层级表征演化融合成熵分数；Llama-3.1\u002F3.2 与 DeepSeek-R1 上不重训、即插即用地超过现有方法。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.26875","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"2d9c2fb0-2be5-4ad1-aedb-e9747addf355","compression",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},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm","2026-06-27T18:14:00Z","2026-06-27T18:15:53.202410Z","2026-06-27T18:15:53.202418Z",true,"agent",2]