2509.09782 2025-09-15 cs.LG One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection Roshini Pulishetty, Mani Kishan Ghantasala, Keerthy Kaushik Dasoju, Niti Mangwani, Vishal Garimella, Aditya Mate, Somya Chatterjee, Yue Kang, Ehi Nosakhare, Sadid Hasan, Soundar Srinivasan 机构 * University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校) ; Microsoft(微软公司) 纠错 详情 展开后加载摘要… URL PDF HTML 收藏 复制 复制简介 复制详情 生成图片 生成简图 生成详图