Song, G., Liao, D., Zhao, Y., Ye, K., Xu, C., & Gao, X. (2025). Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization.
Chicago Style (17th ed.) CitationSong, Guanghui, Dongping Liao, Yiren Zhao, Kejiang Ye, Cheng-zhong Xu, and Xitong Gao. Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization. 2025.
MLA (9th ed.) CitationSong, Guanghui, et al. Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization. 2025.
Warning: These citations may not always be 100% accurate.