SOFT: Softmax-free Transformer with Linear Complexity

Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, Li Zhang. SOFT: Softmax-free Transformer with Linear Complexity. In Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pages 21297-21309, 2021. [doi]

Authors

Jiachen Lu

This author has not been identified. Look up 'Jiachen Lu' in Google

Jinghan Yao

This author has not been identified. Look up 'Jinghan Yao' in Google

Junge Zhang

This author has not been identified. Look up 'Junge Zhang' in Google

Xiatian Zhu

This author has not been identified. Look up 'Xiatian Zhu' in Google

Hang Xu

This author has not been identified. Look up 'Hang Xu' in Google

Weiguo Gao

This author has not been identified. Look up 'Weiguo Gao' in Google

Chunjing Xu

This author has not been identified. Look up 'Chunjing Xu' in Google

Tao Xiang

This author has not been identified. Look up 'Tao Xiang' in Google

Li Zhang

This author has not been identified. Look up 'Li Zhang' in Google