arXiv:2609.10317v1 Announce Type: new
Abstract: Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite directio...
By Yanru An, Ruiyan Wang, Wenwu Wei, Rui Bu, Qi Wang, Hongwei Hu, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang
arXiv:2608.05663v3 Announce Type: replace
Abstract: Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual co...
By Menglin Han, Yang Ding, Yulei Lu, Haoran Yu, Xin Ma, Junyi Chen, Zhangkai Ni, Lin Ma, Yaohui Wang
Real-time long-form avatar audio--video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas.
arXiv:2610.35594v1 Announce Type: new
Abstract: Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has...
By Junyi Chen, Haiyu Zhang, Zhoujie Fu, Tengfei Wang, Chunchao Guo
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. By confining bidirectional spatio‑temporal modeling to a fixed‑size window and using bounded temporal and global appearance memories, it emits clean video chunks with low latency. A progressive distillation pipeline further refines the model, achieving superior quality with 26× lower latency and 11× higher throughput compared to prior methods.
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. It preserves bounded bidirectional modeling within a fixed‑size window, emits clean video chunks iteratively, and uses two memory modules—a bounded temporal memory and a persistent global appearance memory—to sustain long‑term consistency. A progressive distillation process further aligns teacher‑based bidirectional learning with causal few‑step inference, resulting in superior generation quality with 26× lower latency and 11× higher throughput compared to comparable models.
By Yushe Cao, Shikun Feng, Ruxiang Duan, Liyong Wang, Dianxi Shi, Chun Yu, Junliang Xing