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

Media reports Hugging Face Papers Source language: Chinese

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…

Full text

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.

Sources

← Back to Daily AI Report