Clean Forcing: Drift-Resistant Autoregressive Video Diffusion with a Frozen Base
视频扩散漂移修正研究，无开放模型，仅背景参考
Autoregressive (AR) video diffusion models generate streaming video of arbitrary length by conditioning each new chunk of frames on those already generated. However, they suffer from exposure bias, where a model trained on clean context must continue from its own imperfect output
判断口径 agnes-3.0-flash · 入库 #69 · 回首页