AI Paper Atlas

Research map / Video / Video generation

Learning Transferable Dynamics Priors from Action to World Modeling

Ze Huang, Zhang Jiahui, Hairuo Liu, Chenxi Zhang, Ran Cheng, Li Zhang

ECCV 2026 · Video › Video generation · approach: World-model video generation · 8 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
action-conditioned pretraining instead of text-conditioned pretraining (rollout) (ablation)A2World-sim · LIBERO rolloutPSNR: 26.18 -> 26.64Improved
action-conditioned pretraining instead of text-conditioned pretraining (rollout) (ablation)A2World-sim · Real robot rollout (Flexiv Rizon 4S)PSNR: 24.64 -> 25.95Improved
add pose-guided history sampling versus no history (ablation)A2World-sim · LIBERO rolloutPSNR: 25.41 -> 26.64Improved
add pose-guided history sampling versus sliding window (ablation)A2World-sim · LIBERO rolloutPSNR: 25.63 -> 26.64Improved
add pose-guided history sampling versus sliding window (ablation)A2World-sim · LIBERO rolloutEPE: .3900 -> .3498Improved
action-to-video pretraining instead of Cosmos initialization (OOD policy) (ablation)A2World-policy · LIBERO-Plus Spatialsuccess rate: 80.2 -> 88.5Improved
action-to-video pretraining instead of text-conditioned pretraining (OOD policy) (ablation)A2World-policy · LIBERO-Plus Spatialsuccess rate: 85.8 -> 88.5Improved
policy-targeted pretraining instead of action-to-video pretraining (OOD) (ablation)A2World-policy · LIBERO-Plus Spatialsuccess rate: 88.5 -> 88.6No clear effect
action-to-video pretraining instead of Cosmos initialization (in-domain) (ablation)A2World-policy · LIBEROsuccess rate: 97.0 -> 98.6Improved
action-to-video pretraining instead of text-conditioned pretraining (in-domain) (ablation)A2World-policy · LIBEROsuccess rate: 97.4 -> 98.6Improved
policy-targeted pretraining instead of action-to-video pretraining (in-domain) (ablation)A2World-policy · LIBEROsuccess rate: 98.6 -> 98.8No clear effect
train video branch jointly instead of freezing it (ablation)A2World-policy · LIBEROsuccess rate: 86.2 -> 98.6Improved

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