AI Paper Atlas

Research map / Video / Video generation

MemLearner: Learning to Query Context Memory for Video World Models

Jiwen Yu, Jianxiong Gao, Jianhong Bai, Yiran Qin, Kaiyi Huang, Quande Liu, Xintao Wang, Pengfei Wan, Kun Gai, Xihui Liu

ECCV 2026 · Video › Video generation · approach: World-model video generation · 6 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 Q-to-P attention for query tokens (ablation)MemLearner · collected dataset GT Comp.PSNR: 17.27 -> 21.23Improved
add Q-to-Q attention (ablation)MemLearner · collected dataset GT Comp.PSNR: 21.23 -> 21.19No clear effect
add context tokens as queries in attention (ablation)MemLearner · collected dataset GT Comp.PSNR / fps: 21.23 -> 21.34 PSNR; 0.54 -> 0.28 fpsNo clear effect
increase query layers from 1 to 5 (ablation)MemLearner · collected dataset GT Comp.PSNR: 18.16 -> 21.23Improved
increase query layers from 5 to 20 (ablation)MemLearner · collected dataset GT Comp.PSNR / fps: 21.23 -> 21.37 PSNR; 0.54 -> 0.36 fpsNo clear effect
add camera pose embeddings to C and Q tokens (ablation)MemLearner · collected dataset GT Comp.PSNR: 21.17 -> 21.23No clear effect
init Q tokens with random noise instead of noisy P tokens (ablation)MemLearner · collected dataset GT Comp.PSNR: 21.17 -> 21.23No clear effect
add rendered occlusion dataset (Ours) to CaM training (ablation)MemLearner · Revisit Comp.PSNR: 18.35 -> 18.57Improved
train on real-world data only (ablation)MemLearner · Revisit Comp.PSNR: 18.57 -> 15.32Hurt
add real-world data to rendered training (ablation)MemLearner · Real QualityFID: 161.83 -> 115.47Improved
use query module sharing the video model instead of a separate from-scratch module (ablation)Separate Module · collected dataset GT Comp.PSNR: 9.16 -> 21.23Improved
use separately pre-trained query module with L1 supervision instead of end-to-end (ablation)MemLearner · collected dataset GT Comp.PSNR: 21.23 -> 16.56Hurt

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