Ji, Shulei, et al. “Diff-V2M: A Hierarchical Conditional Diffusion Model With Explicit Rhythmic Modeling for Video-to-Music Generation”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 26, Mar. 2026, pp. 22219-27, doi:10.1609/aaai.v40i26.39378.