Cheng, Y., Huang, S., Chen, X., Ning, J., & Gong, M. (2025). DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 2464–2472. https://doi.org/10.1609/aaai.v39i3.32248