Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion

媒体报道 Hugging Face Papers 原文语言:中文

论文摘要(作者报告,未经本站复测):Autoregressive video diffusion models (AR-VDMs) enable real-time, long-horizon video generation but degrade rapidly once the inference horizon outruns the training horizon, due to compounding exposure…

全文

Disen-Forcing is a distillation-time method for autoregressive video diffusion models that disentangles attention-head specialization to improve long-range consistency and motion dynamics in long-horizon video generation.

正文以来源语言显示。

参考来源

← 返回每日AI报告