Papers
arxiv:2503.10704

Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework

Published on Mar 12
· Submitted by k-nick on Mar 18
Authors:
,

Abstract

A variety of Auto-Regressive Video Diffusion Models (ARVDM) have achieved remarkable successes in generating realistic long-form videos. However, theoretical analyses of these models remain scant. In this work, we develop theoretical underpinnings for these models and use our insights to improve the performance of existing models. We first develop Meta-ARVDM, a unified framework of ARVDMs that subsumes most existing methods. Using Meta-ARVDM, we analyze the KL-divergence between the videos generated by Meta-ARVDM and the true videos. Our analysis uncovers two important phenomena inherent to ARVDM -- error accumulation and memory bottleneck. By deriving an information-theoretic impossibility result, we show that the memory bottleneck phenomenon cannot be avoided. To mitigate the memory bottleneck, we design various network structures to explicitly use more past frames. We also achieve a significantly improved trade-off between the mitigation of the memory bottleneck and the inference efficiency by compressing the frames. Experimental results on DMLab and Minecraft validate the efficacy of our methods. Our experiments also demonstrate a Pareto-frontier between the error accumulation and memory bottleneck across different methods.

Community

Paper author Paper submitter

🚶‍♂️ Ever gotten lost, only to find yourself back at the same spot, struggling to recall what it looked like?

We challenge video generation models with the same problem! 🤯

🔍 Key takeaways from our work:
1️⃣ We first pinpoint error accumulation & memory bottlenecks in autoregressive video diffusion—both theoretically & experimentally.
2️⃣ We reveal a surprising link: better memory retrieval ↔ faster error accumulation.
3️⃣ A simple memory module compresses context into limited tokens while preserving retrieval ability.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2503.10704 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2503.10704 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2503.10704 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.