Zhongzhi Yu, Yonggan Fu, Sicheng Li, Chaojian Li, Yingyan Lin. MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022. pages 8962-8970, AAAI Press, 2022. [doi]