AI Paper Atlas

Research map / Video / Video generation

Vid2World: Crafting Video Diffusion Models to Interactive World Models

Siqiao Huang, Jialong Wu, Qixing Zhou, Shangchen Miao, Mingsheng Long

ICLR 2026 · Video › Video generation · approach: World-model video generation · 71 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 action guidance (action dropout plus classifier-free guidance) with Extrapolative weight transfer (ablation)Vid2World · RT-1 (30k steps)FVD: 28.6 -> 22.4Improved
add action guidance with Masked weight transfer (ablation)Vid2World · RT-1 (30k steps)FVD: 29.4 -> 25.8Improved
use Masked instead of Shift weight transfer (ablation)Vid2World temporal convolutions · RT-1 (30k steps, no guidance)FVD: 29.9 -> 29.4Improved
use Extrapolative instead of Shift weight transfer (ablation)Vid2World temporal convolutions · RT-1 (30k steps, no guidance)FVD: 29.9 -> 28.6Improved
use Extrapolative instead of Masked weight transfer (ablation)Vid2World temporal convolutions · RT-1 (30k steps, with guidance)FVD: 25.8 -> 22.4Improved
use Extrapolative instead of Masked weight transfer, without guidance (ablation)Vid2World temporal convolutions · RT-1 (30k steps, no guidance)FID: 7.07 -> 7.52Hurt
fine-tune video diffusion model with causal training and action conditioning versus pre-trained base modelDynamiCrafter · RT-1FVD: 237.6 -> 18.5Improved
Vid2World instead of DIAMOND-HQworld model · CS:GOFVD: 368.5 -> 106.6Improved
Vid2World instead of DIAMOND-HQworld model · CS:GOFID: 87.2 -> 17.5Improved
Vid2World autoregressive versus NWM single-stepworld model · RECONFVD / FID: FVD 59.4 vs 31.2; SSIM 0.481 vs 0.389Mixed
autoregressive Vid2World versus non-autoregressive Vid2World-NAR (ablation)Vid2World · RT-1FVD: 18.7 -> 18.5No clear effect
Shift weight transfer may fail on linearly increasing inputs (ablation)temporal convolution causalization · theory (counter-example)approximation errorHurt

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