AI Paper Atlas

Research map / Video / Video generation

Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion

Yuanyu He, Zhuokun Chen, Yefei He, Zhiwei Tang, Jiasheng Tang, Yinghao Yu, Jianfei Cai, Bohan Zhuang

NeurIPS 2026 · Video › Video generation · approach: Efficient video diffusion models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a dynamics-aware sparse attention method for autoregressive video diffusion transformers to reduce computation and memory when generating long videos.

Problem

Autoregressive Diffusion Transformers for long video generation suffer from prohibitive computational overhead and large memory footprints because dense computation allocates uniform resources across all spatiotemporal regions, ignoring temporal redundancy where motion is sparse.

Approach

Uses video dynamics (motion) to allocate sparse attention so that computation concentrates on dynamic regions instead of uniformly over all spatiotemporal positions; details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use layer-wise memory retention (sigma 0.8 to 0.2) instead of uniform 0.6 (ablation)DASA on Self Forcing · VBench 5sthroughput / total score: 24.11 -> 26.21 FPS; 83.30 -> 83.81 totalImproved
uniform retention sigma 0.8 instead of layer-wise (ablation)DASA on Self Forcing · VBench 5sthroughput (FPS): 26.21 -> 22.34Hurt
add motion-aware early exit with local alignment (ablation)Self Forcing · VBench 5sthroughput (FPS): 18.42 -> 26.21Improved
add motion-aware early exit with local alignment (ablation)Self Forcing · VBench 5stotal score: 84.19 -> 83.81Hurt
add dynamics-guided adaptation on top of alignment (ablation)DASA on Self Forcing · VBench 5sthroughput and semantic score: 26.21 -> 27.58 FPS; semantic 80.77 -> 81.32Improved
increase max age threshold tau for static token refresh to 6 or more (ablation)DASA · VBench 5svisual qualityHurt
use early-exit threshold gamma=0.92 (ablation)DASA · VBench 5sspeedup / total score: 1.42x speedup, total 83.98Improved
apply DASA instead of Dummy ForcingSelf Forcing · VBench 1080Pthroughput and total score: 2.64 -> 2.81 FPS; 82.46 -> 82.79Improved
apply DASA to LongLive at 720PLongLive · VBench 720Ptotal score: 83.31 -> 83.01Hurt

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