ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

  • 类型:arxiv
  • 标识:2609.28923
  • 链接:https://arxiv.org/abs/2609.28923
  • 主分类:multimodal
  • 形态:method
  • TLDR:Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both a large pretrained teacher and an online critic to estimate distributional discrepancies through diffusion scores. In this work, we ask whether this resource-intensive teacher--critic stack can be eliminated by post-training only the generator against a precomputed target distribution. Drawing inspiration from representation distribution matching (RDM) for one-step image generation, we systematic
  • 副分类:engineering
  • 待LLM分类:否
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-25-agent-rag-longcontext-candidates.json