@article{transformersaressmsgeneralizedmodelsand, title = {Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality}, author = {Tri Dao and Albert Gu}, year = {2024}, eprint = {2405.21060}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.21060v1}, }