Lu, Zhu, et al. “R-AVST: Empowering Video-LLMs With Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 9, Mar. 2026, pp. 7627-35, doi:10.1609/aaai.v40i9.37704.