Preprint
Jul 2026
Mitigating Compounding Error via Video Representation Regularization
This work establishes the first connection between autoregressive video drifting and model internal representations, adopts erank as a quantitative metric for error accumulation, reveals counterintuitive scaling limitations for video world models, and presents a simple yet effective regularization strategy to improve long video generation robustness.
Taiye Chen, Qi Zhang, Yisen Wang
· 0 citations