AI Paper Atlas

Research map / Video / Video generation

DynaMem: Consistent Long Video Generation via Hierarchical Memory and Motion Priors

Jingyu Lin, Xinyi Shang, Peng Sun, Cunjian Chen, Zhiqiang Shen

ICML 2026 · Video › Video generation · approach: Autoregressive long video generation

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 curated prompt-guided memory retrieval instead of last frame only (ablation)DynaMem · LV-BenchVDE Subject: 1.2190 -> 0.0753Improved
add motion-driven references instead of last frame only (ablation)DynaMem memory · LV-BenchVDE Subject: 1.2190 -> 0.6547Improved
curate memory instead of retrieving from all frames (ablation)DynaMem · LV-BenchVDE Subject: 0.1845 -> 0.0753Improved
curate memory instead of retrieving from all frames (ablation)DynaMem · LV-Bench VBenchAesthetic Quality: 0.6534 -> 0.6881Improved
curate memory instead of retrieving from all frames (ablation)DynaMem · LV-Bench VBenchMotion Smoothness: 0.9961 -> 0.9956No clear effect
add motion-prioritized optimization over Ldiff only (ablation)DynaMem · LV-BenchVDE Motion: 0.0537 -> 0.0096Improved
add motion-aware SFT to Ldiff only (ablation)DynaMem training · LV-BenchVDE Motion: 0.0537 -> 0.0243Improved
full MPO with gradient-based data selection over motion SFT only (ablation)DynaMem training · LV-BenchVDE Subject: 0.3429 -> 0.0753Improved
add RAPA perceptual alignment (ablation)DynaMem · 1-minute generationsIQA at 60s: 1.67 -> 1.97Improved
add RAPA perceptual alignment (ablation)DynaMem · 1-minute generationsIQA at 10s: 1.98 -> 1.99No clear effect

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