Zhong Zhang 0004, Nian Shao, Chongming Gao, Rui Miao, Qinli Yang, Junming Shao. Mixhead: Breaking the low-rank bottleneck in multi-head attention language models. Knowl.-Based Syst., 240:108075, 2022. [doi]
@article{0004SGMYS22, title = {Mixhead: Breaking the low-rank bottleneck in multi-head attention language models}, author = {Zhong Zhang 0004 and Nian Shao and Chongming Gao and Rui Miao and Qinli Yang and Junming Shao}, year = {2022}, doi = {10.1016/j.knosys.2021.108075}, url = {https://doi.org/10.1016/j.knosys.2021.108075}, researchr = {https://researchr.org/publication/0004SGMYS22}, cites = {0}, citedby = {0}, journal = {Knowl.-Based Syst.}, volume = {240}, pages = {108075}, }