CAO, Jiajun et al. FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 4, p. 2571–2579, 2026. DOI: 10.1609/aaai.v40i4.37244. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37244. Acesso em: 26 may. 2026.