Story

arxiv_cs_ai ยท Nov 19, 2026 ยท paper

Source brief

AURA: AUdio-dRiven streaming Avatar

arxiv.orgNov 19, 2026
original source linked

In brief

Current audio-driven video diffusion models can synthesize realistic talking-head videos but generally require dozens of diffusion denoising steps over multi-second video chunks, making them unsuitable for streaming a...

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items