AI Paper Atlas

Research map / Video / Video generation

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Weijie Wang, Xiaoxuan He, Youping Gu, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang

ICML 2026 · Video › Video generation · approach: Autoregressive long video generation · 0 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
fine-tune with World-R1 RL alignment (Small)Wan2.1-T2V-1.3B · 3D consistencyPSNR: 17.40 -> 27.63Improved
fine-tune with World-R1 RL alignment (Large)Wan2.1-T2V-14B · 3D consistencyPSNR: 19.76 -> 27.67Improved
fine-tune with World-R1 RL alignment (Small)Wan2.1-T2V-1.3B · 3D consistencyLPIPS: 0.467 -> 0.201Improved
fine-tune with World-R1 RL alignment (Small)Wan2.1-T2V-1.3B · VBenchAesthetic Quality: 62.43 -> 65.74Improved
fine-tune with World-R1 RL alignment (Small)Wan2.1-T2V-1.3B · VBenchBackground Consistency: 97.29 -> 96.67Hurt
fine-tune with World-R1 RL alignment (Small)Wan2.1-T2V-1.3B · VBenchMotion Smoothness: 97.44 -> 98.55Improved
add the 3D-aware reward R_3D (ablation)World-R1-Small · reward ablationgeometric consistencyImproved
add the general generation reward R_gen (ablation)World-R1-Small · reward ablationperceptual fidelityImproved
add implicit camera injection via noise warping (ablation)World-R1-Small · convergence and trajectory alignmentconvergence speed and trajectory alignmentImproved
add periodic decoupled dynamic fine-tuning (ablation)World-R1-Small · dynamic motionnon-rigid dynamicsImproved

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