Skip to content
InfoResearchPeer-reviewed

Error Analyses of Auto-Regressive Video Diffusion Models

Published
Record updated
View JSON

Summary

Meta-ARVDM is a unified analytical framework that studies history forgetting and temporal degradation in Auto-Regressive Video Diffusion Models (AR-VDMs). The authors show that history forgetting is characterized by the conditional mutual information between the generated output and preceding frames, and prove that adding more past frames monotonically alleviates it. They also show that temporal degradation can be quantified by the cumulative sum of per-step errors, and report a strong empirical correlation between the two phenomena.