AI Paper Atlas

Research map / Video / Video generation

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos

Zhongwei Ren, Yunchao Wei, Xiao Yu, Guixun Luo, Yao Zhao, Bingyi Kang, Jiashi Feng, Xiaojie Jin

CVPR 2026 · Video › Video generation · approach: World-model video generation · 9 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
replace the original LDM decoder with a pretrained video diffusion model (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 0.0 -> 30.3Improved
stop gradient from the original decoder to latent codes (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 30.3 -> 47.3Improved
add reconstructed video as ControlNet-like condition (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 47.3 -> 68.8Improved
increase query embedding length from 1 to 4 (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 41.9 -> 68.8Improved
increase query embedding length from 4 to 8 (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 68.8 -> 65.0Hurt
enlarge codebook from 1000 to 64,000 (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 68.8 -> 29.4Hurt
enlarge codebook from 1000 to 4096 (ablation)dLDM · CALVIN avg. lengthAvg. Len.: 1.87 -> 1.90No clear effect
use short T=2 context instead of 93 frames (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 68.8 -> 19.1Hurt
increase context from 93 to 177 frames (ablation)dLDM · Video-CraftBench paper foldingsuccess rate (%): 68.8 -> 69.0No clear effect
use VideoWorld 2 latent codes instead of VideoWorld on Craft-only trainingVideoWorld · Video-CraftBench paper folding step 7success rate (%): 0.0 -> 68.8Improved
add OpenX pretraining of the latent modelVideoWorld 2 · Video-CraftBench paper folding step 7success rate (%): 68.8 -> 72.3Improved
add OpenX latent pretrainingVideoWorld 2 · CALVIN ABCD->DAvg. Len.: 2.36 -> 2.88Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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