Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

arXiv 2025 34.3 method

TLDR

Wan-Move enables precise motion control in video generation by projecting dense point trajectories into latent space, guiding an off-the-shelf I2V model without architectural changes.

Reasoning

The paper presents a scalable framework for motion-controllable video generation with a novel latent trajectory guidance method, validated via user studies and a new benchmark. However, it does not address world models or dynamics prediction, and the abstract lacks details on limitations or broader implications.

Read-first score

Read-first score 34.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 1.

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=benchmark,dataset,evaluation,experiment

Reproducibility 25%

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

Topical relevance 42%

1.4

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: 214.

Keyword Scores

video world model

world model

world simulator

generative world model

interactive world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper