AI Paper Atlas

Research map / Video / Video generation

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Jianzong Wu, Liang Hou, Haotian Yang, Ye Tian, Pengfei Wan, Di ZHANG, Yunhai Tong

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models · 36 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
add 3D blocks to 1-2D partition (1-2-3D) (ablation)VMoBA · Block partition ablation (Training 93x576x1024)SubConsist: 86.12% -> 94.72%Improved
add 2D blocks to 1-3D partition (ablation)VMoBA · Block partition ablation (Training 93x576x1024)SubConsist: 91.34% -> 94.72%Improved
add 1D temporal blocks to 2-3D partition (ablation)VMoBA · Block partition ablation (Training 93x576x1024)SubConsist: 94.75% -> 94.72%No clear effect
use global block selection instead of local (ablation)VMoBA · Block selection ablationSubConsist: 92.43% -> 94.72%Improved
use threshold selection instead of top-k (global) (ablation)VMoBA · Block selection ablationSubConsist: 92.86% -> 94.72%Improved
raise tau from 0.15 to 0.25 (ablation)VMoBA · Threshold tau ablationSubConsist: 91.12% -> 94.72%Improved
raise tau from 0.25 to 0.50 (ablation)VMoBA · Threshold tau ablationSubConsist: 94.72% -> 94.42%No clear effect
more blocks 24-48-144 vs 8-48-72 (ablation)VMoBA · Number of blocks ablationSubConsist: 94.72% -> 94.42%No clear effect
fewer blocks 8-24-36 vs 8-48-72 (ablation)VMoBA · Number of blocks ablationSubConsist: 94.72% -> 93.59%Hurt
VMoBA instead of MoBA in trainingWan 2.1 (93x576x1024) · Trainingtraining time: 226 -> 187 GPU HoursImproved
VMoBA instead of MoBA in training-free 81x480x832Wan 2.1 · Training-free 81x480x832latency: 126s -> 104sImproved
VMoBA instead of full attention trainingWan 2.1 (93x576x1024) · Trainingtraining time: 276 -> 187 GPU HoursImproved

Later papers that compared with this method

4 later accepted papers report VMoBA as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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