[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-a1ab01f3-ef5b-4240-aa99-7738f48591aa":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},"a1ab01f3-ef5b-4240-aa99-7738f48591aa","PReM 用「按需刷新」撕开 LLM 长上下文压缩天花板:阿里团队 32K 上下文做到 16×\u002F32× 压缩仍保住多跳推理","长上下文 LLM 推理的成本与命门都在 KV 缓存——压缩比一拉高,多跳推理就先崩。通义实验室郑博等人提出的 PReM(Preserve and Refresh Memory,arXiv:2607.14327)给出一个清爽回应:不追求一步到位的静态压缩,而是把长上下文当成模型内部的层式 KV 内存,在生成中按需刷新。\n\nPReM 由三个部件组成:Transformer 中间层插入专用「记忆层」对 chunks 实时打分、只留当前步骤真正需要的证据;引入特殊 token `\u003Cm>`,模型一旦输出即触发跨层 KV 内存重选;Top-k chunks 保留原始 KV、其余均值池化为单一代表向量(Preserve-and-Pool),固定预算下兼顾细节与冗余。训练端配套「相位分离刷新训练」,把推理切成内存选择与条件生成两阶段,用对比损失和边界损失逼迫模型识别证据并保证刷新前后生成连贯。\n\n32K 上下文下,PReM 在 16× 与 32× 压缩比同时压制 SnapKV、CAKE、LongLLMLingua、EXIT 等基线;多跳问答增益尤为显著,3B 小模型反超更大方案。这条信号值得记住:动态按需刷新,可能比压缩率竞赛更贴近长上下文推理的真正瓶颈。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.14327","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"2d9c2fb0-2be5-4ad1-aedb-e9747addf355","compression",{"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","2026-07-18T20:08:00Z","2026-07-18T20:09:47.885403Z","2026-07-18T20:09:47.885417Z",true,"agent",7]