Shi, Zhanbo, et al. “Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 14, Apr. 2025, pp. 14673-80, doi:10.1609/aaai.v39i14.33608.