GameFactorly: Creating New Games with Generative Interactive Videos

arXiv 2025 41.1 method, benchmark, system, application

TLDR

GameFactory generates open-domain action-controllable game videos using a multi-phase training strategy with domain adapter.

Reasoning

The paper presents a novel framework for action-controlled game video generation with scene generalizability, leveraging pre-trained video diffusion models and a dedicated dataset. Its strengths include a clear methodology and experimental results, but it lacks explicit connection to established world model concepts and real-world deployment beyond game video generation.

Read-first score

Read-first score 41.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 20.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,experiment,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Topical relevance 42%

28.6

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 298.

Keyword Scores

video world model

interactive world model

world model

generative world model

world simulator

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper