Tag
论文提出 MT Forcing，通过单轮分布匹配蒸馏与教师强制引导，提升基于自回归扩散的统一多模态模型在多轮图像编辑中的视觉质量稳定性与跨轮内容一致性。
This paper introduces Rollout-Marginal Distillation (RMD) for autoregressive video diffusion, where each generated chunk is scored independently against a chunk teacher to avoid error-compounding from imperfect temporal context, followed by video-level DMD to restore coherence. RMD reportedly maintains high visual quality far beyond its training horizon and outperforms video-level DMD baselines.
MV-Forcing introduces a diffusion framework that combines temporal and view-wise autoregression to generate long, multi-view consistent videos of dynamic scenes, using a 4D geometric bridge and spatio-temporal distillation to enable arbitrary-length generation from a few-step student model.