HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization 文章

ArXiv CS.CL2026-06-19NEWSen作者: Zhentao Tan, Wei Chen, Jingyi Shen, Yao Liu, Xu Shen, Yue Wu, Jieping Ye

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization · 相关技术