AI Paper Atlas

Research map / Video / Video generation

GameFactory: Creating New Games with Generative Interactive Videos

Jiwen Yu, Yiran Qin, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu

ICCV 2025 · Video › Video generation · approach: World-model video generation · 87 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
use cross-attention instead of concatenation for keyboard actions (ablation)action control module · Only-Key subsetCam: 0.0853 -> 0.0439Improved
use cross-attention instead of concatenation for keyboard actions (ablation)action control module · Only-Key subsetFlow: 22.37 -> 7.79Improved
use concatenation instead of cross-attention for mouse movement (ablation)action control module · Mouse-Small subsetCam: 0.0798 -> 0.0685Improved
use concatenation instead of cross-attention for mouse movement (ablation)action control module · Mouse-Large subsetFlow: 325.18 -> 249.54Improved
use concatenation instead of cross-attention for mouse movement (ablation)action control module · Mouse-Large subsetCam: 0.1362 -> 0.1021Improved
change key/mouse fusion mechanism (ablation)action control module · Only-Key / Mouse CLIP, FID, FVDCLIP/FID/FVDNo clear effect
add multi-phase decoupled training with domain adapter instead of one-phase (ablation)GameFactory · open-domain scene generalizationCam: 0.1134 -> 0.0997Improved
add multi-phase decoupled training instead of one-phase (ablation)GameFactory · open-domain scene generalizationFlow: 76.02 -> 54.13Improved
add multi-phase decoupled training instead of one-phase (ablation)GameFactory · open-domain scene generalizationFID: 167.79 -> 121.18Improved
add multi-phase decoupled training instead of one-phase (ablation)GameFactory · open-domain scene generalizationDom: 0.7345 -> 0.7565Improved
train on GF-Minecraft instead of VPT (ablation)action control model · in-domain evaluationFID: 156.69 -> 125.85Improved
train on GF-Minecraft instead of VPT (ablation)action control model · in-domain evaluationFlow: 107.67 -> 43.48Improved

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