Lu Gan Zhigui Chen Qian Hu Xiaolin Tang Xiao Luo Wenbo Chu Guofa Li Performance and lightweight coexistence: Vision-language model for visual scene question answering in autonomous driving. 2026 104424 71 Adv. Eng. Informatics https://doi.org/10.1016/j.aei.2026.104424 db/journals/aei/aei71.html#GanCHTLCL26 streams/journals/aei