Jul 2026
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
Results show that \method preserves stable appearance across prompt-conditioned segments and strong audio-visual synchronization under autoregressive generation, accelerating autoregressive inference without pipeline-specific retraining.
Qijun Gan, Chen-Wei Zhang, Mei-Guang Jin et al.
· arXiv.org · 0 citations