Paper notes

ViMo: A Generative Visual GUI World Model for App Agents

Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao

First arXiv submission: April 15, 2025 · arXiv

Predicts future mobile-app screens to help agents compare possible actions, separating graphic content from textual content.

Read paper ↗

Contribution and setting

Uses symbolic text placeholders to preserve layout while assigning graphical and text prediction to separate components.

Model output

Future mobile GUI images assembled from graphics and text predictions.

Action interface

Candidate mobile-app actions.

State and memory

Screen-and-action-conditioned prediction; symbolic text representation retains text locations and layout.

Relationship to NeuralOS

Visual GUI world-model research released in April 2025, before NeuralOS's July 2025 preprint.

Source ↗

Scope and limitations

The experiments predict mobile-app screens for agent planning.

Related terms: ViMo, GUI world model, next-screen prediction, mobile app simulation.

Read or reuse this entry

JSON record · Markdown · Find in the full list