YU, Zhongzhi; FU, Yonggan; LI, Sicheng; LI, Chaojian; LIN, Yingyan. MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 36, n. 8, p. 8962–8970, 2022. DOI: 10.1609/aaai.v36i8.20879. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/20879. Acesso em: 7 may. 2026.