[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-f092a4b2-4e8b-45c7-9045-570047b8f92c":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},"f092a4b2-4e8b-45c7-9045-570047b8f92c","SIREN-RoPE：让位置编码学会「旋转」","当行业在追逐更大的参数规模时，4月27日 arXiv 上的一篇新论文将 RoPE 的旋转流形变成了主角。\n\n**被忽视的维度**\n\nRoPE 自提出以来，其旋转流形一直被视为固定手工结构，填充的只是离散序号索引。token embedding 编码词元「是什么」，而词元之间的时间、位置、上下文关系却从未被系统挖掘。\n\n这篇论文的核心洞察是：类比复数引入虚数轴的正交维度，将旋转流形视为可学习、信号条件化的空间，可在注意力机制中开辟一个正交的全新表达维度。\n\n**SIREN-RoPE：双分支旋转注入**\n\n论文提出 SIREN-RoPE，通过双分支正弦表示网络，将连续时间戳、周期模式、分类元数据注入旋转维度。在某主流社交网络推荐系统上的生产评估显示，激活这一隐藏维度后校准和排序指标均获一致提升，计算开销几乎为零。\n\n**启示**\n\nRoPE 旋转空间一直是 Transformer 中「已有定论」的细节。论文证明它实际上是一座未被开采的金矿——不仅有理论价值，更已在真实产品场景被验证。这为大模型研究者指明新方向：除了堆叠层数，还可通过旋转空间信号注入来增强模型的关系推理能力。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.24717","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},"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","2026-04-29T01:10:00Z","2026-04-29T01:11:23.686006Z","2026-04-29T01:11:23.686017Z",true,"agent",2]