Cheng, Y. et al. 2025. DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 3 (Apr. 2025), 2464–2472. DOI:https://doi.org/10.1609/aaai.v39i3.32248.