Linqing Liu, Xiaolong Xu 0002. Self-attention Mechanism at the Token Level: Gradient Analysis and Algorithm Optimization. Knowl.-Based Syst., 277:110784, October 2023. [doi]
@article{LiuX23-11,
title = {Self-attention Mechanism at the Token Level: Gradient Analysis and Algorithm Optimization},
author = {Linqing Liu and Xiaolong Xu 0002},
year = {2023},
month = {October},
doi = {10.1016/j.knosys.2023.110784},
url = {https://doi.org/10.1016/j.knosys.2023.110784},
researchr = {https://researchr.org/publication/LiuX23-11},
cites = {0},
citedby = {0},
journal = {Knowl.-Based Syst.},
volume = {277},
pages = {110784},
}