Fan, Jugang, Peihao Chen, Changhao Li, Qing Du, Jian Chen, and Mingkui Tan. “NaVLA$^2$: A Vision-Language-Audio-Action Model for Multimodal Instruction Navigation”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 22 (March 14, 2026): 18234–18242. Accessed May 9, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/38886.