AI Paper Atlas

Research map / Video / Video generation

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

Yuwei Guo, Ceyuan Yang, Hao He, Yang Zhao, Meng Wei, Zhenheng Yang, Weilin Huang, Dahua Lin

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 49 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use autoregressive resampling instead of noise augmentation (ablation)Resampling Forcing · VBench 15s (0-15s)Temporal quality: 87.15 -> 90.46Improved
use autoregressive resampling instead of noise augmentation (ablation)Resampling Forcing · VBench 15s (0-15s)Visual quality: 61.90 -> 64.25Improved
use autoregressive resampling instead of noise augmentation (ablation)Resampling Forcing · VBench 15s (0-15s)Text alignment: 21.44 -> 25.26Improved
use autoregressive instead of parallel resampling (ablation)Resampling Forcing · VBench 15s (0-15s)Temporal quality: 88.01 -> 90.46Improved
use autoregressive instead of parallel resampling (ablation)Resampling Forcing · VBench 15s (0-15s)Visual quality: 62.51 -> 64.25Improved
use autoregressive instead of parallel resampling (ablation)Resampling Forcing · VBench 15s (0-15s)Text alignment: 24.51 -> 25.26Improved
use 75% sparse history routing instead of dense attention (ablation)Resampling Forcing · VBench 15s (10-15s)Temporal quality: 89.74 -> 87.03Hurt
use 75% sparse history routing instead of dense attention (ablation)Resampling Forcing · VBench 15s (0-5s)Temporal quality: 91.20 -> 90.18Hurt
reduce routing from top-5 to top-1 (95% sparsity) (ablation)history routing · qualitative fish videoappearance consistencyHurt
use dynamic history routing instead of sliding window of size 1 at equal sparsity (ablation)history routing · qualitative fish videoappearance consistencyImproved
use very small timestep shifting factor s (ablation)self-resampling · qualitativeerror accumulationHurt
use very large timestep shifting factor s (ablation)self-resampling · qualitativesemantic consistencyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy