Motion Tokenizer

EchoAvatar: Real-time Generative Avatar Animation from Audio Streams

Bohong Chen, Yumeng Li, Yinglin Xu, Youyi Zheng, Yanlin Weng, Kun Zhou

Conference SIGGRAPH 2026 Streaming Motion Generation Audio-Driven Animation Co-Speech Gesture Music-To-Dance Motion Tokenizer Residual Vector Quantization Reinforcement Learning Real-Time Animation Large Language Model