Kim S, Jin S, Park J, Kim K, Kim J, Nam J, et al. MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 11];39(4):4302-10. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32452