cs.CVOct 31, 2026

What Helps Denoising Can Hurt Memory: Rethinking History in Long Video Generation

Authors: Yubin Jing, Ziyang Zhang, Meng Chen, Yuyao Li, Haofan Wang, Yichen Gong

Organizations: Georgia Institute of Technology · Peking University · Zhejiang University · Tsinghua University · 

Abstract

Autoregressive video generators produce long videos block by block, using historical context to maintain temporal consistency. After denoising, a committing pass encodes each clean block into keys and values (KV) that later blocks read, and the same clean block can be encoded into different KV depending on the history it reads. We therefore study historical context not only as a condition for denoising but also as an input to committing. Older historical context that supports denoising can harm subsequent generation when read during committing. At fixed context size and temporal positions, older historical context lowers mean clip-to-clip Subject Consistency. Across 5 generator configurations supporting longer contexts, consistency rises, plateaus, and then declines as committing context expands. Motivated by these findings, we propose Commit Forcing, a training-free rule that organizes committing into a chain. During committing, each block reads only the preceding block's stored KV, so older historical context reaches new entries only through the chain. We apply this rule to 6 pretrained generators. On 60-second VBench, Commit Forcing improves Quality and Total on all 6 generators, by up to 1.27 Quality points and 1.10 Total points. Long-range consistency gains extend to 240-second videos. In a blinded comparison on 120-second LongLive videos, Commit Forcing achieves win rates of 83.5% for subject and scene consistency and 82.9% for overall preference against the base generator, excluding ties.

Figures & tables

Appendix figures & tables48 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Recast the Past: Stable Long Video Generation with Full Context Memory

    Oct 20, 2026Yukuo Ma, Cong Liu, Junke Wang +4Long-Horizon Video GenerationMemory-Augmented Video Generation

  2. Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation

    Sep 28, 2026Xiaoyu Wu, Weihang Guo, Yifei Wang +3Video Diffusion ModelsLong Video Generation

  3. History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models

    Nov 2, 2026Hangyi Kuang, Chengzhi Wang, Yefei He +8Video GenerationLong-Horizon Video Generation