Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Autoregressive video diffusion extends diffusion distillation frameworks to real-time streaming generation through causal training paradigms, achieving state-of-the-art performance…

Hugging Face · Daily Papers ·Kaiwen Zheng, Guande He · ·▲ 10 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Kaiwen Zheng, Guande He, Min Zhao, Jintao Zhang, Huayu Chen, Jianfei Chen

  • 10 upvotes da comunidade
  • Temas: autoregressive video diffusion, causal diffusion transformers, diffusion distillation, consistency models, distribution matching distillation, teacher-forcing

Resumo

Resumo original (em inglês), extraído do paper:

Autoregressive video diffusion extends diffusion distillation frameworks to real-time streaming generation through causal training paradigms, achieving state-of-the-art performance with fast convergence and interactive world modeling capabilities.

Ler o paper completo no Hugging Face →

compartilhar: