Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

7 words

1 minute

2025-12-26

Deep Learning

/

Mamba

Tri Dao, Albert Gu

Paper link: https://arxiv.org/abs/2405.21060

Slide

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Author

Po-Yu Chiu

Published at

2025-12-26

License