Wan-Streamer is a unified end-to-end Transformer for low-latency streaming audio-visual interaction using block-causal attention on interleaved multimodal tokens.
Body of her: A preliminary study on end-to-end humanoid agent
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.
citing papers explorer
-
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Wan-Streamer is a unified end-to-end Transformer for low-latency streaming audio-visual interaction using block-causal attention on interleaved multimodal tokens.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.