{"ID":2832934,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.04677","arxiv_id":"2512.04677","title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","abstract":"Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon drift of current diffusion models. We present Live Avatar, an algorithm-system co-designed framework that addresses both challenges for a 14-billion-parameter diffusion model. On the algorithm side, a two-stage pipeline distills a pretrained bidirectional model into a causal, few-step streaming one, while a set of complementary long-horizon strategies eliminate identity drift and visual artifacts, enabling stable autoregressive generation exceeding 10000 seconds. On the system side, Timestep-forcing Pipeline Parallelism (TPP) assigns each GPU a fixed denoising timestep, converting the sequential diffusion chain into an asynchronous spatial pipeline that simultaneously boosts throughput and improves temporal consistency. Live Avatar achieves 45 FPS with a TTFF of 1.21\\,s on 5 H800 GPUs, and to our knowledge is the first to enable practical real-time streaming of a 14B diffusion model for infinite-length avatar generation. We further introduce GenBench, a standardized long-form benchmark, to facilitate reproducible evaluation. Our project page is at https://liveavatar.github.io/.","short_abstract":"Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon drift of current diffusion models. We present Live Avatar, an algorithm-system co-designed framework that addresses both challenges for a 14-b...","url_abs":"https://arxiv.org/abs/2512.04677","url_pdf":"https://arxiv.org/pdf/2512.04677v5","authors":"[\"Yubo Huang\",\"Hailong Guo\",\"Fangtai Wu\",\"Weiqiang Wang\",\"Shifeng Zhang\",\"Shijie Huang\",\"Qijun Gan\",\"Lin Liu\",\"Sirui Zhao\",\"Enhong Chen\",\"Jiaming Liu\",\"Steven Hoi\"]","published":"2025-12-04T11:11:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}