Cheng Y, Huang S, Chen X, Ning J, Gong M. DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 9];39(3):2464-72. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32248