Cheng, Yongkang, et al. “DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-Time Gesture Generation from Speech”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 3, Apr. 2025, pp. 2464-72, doi:10.1609/aaai.v39i3.32248.