Tell Me What's Next: Textual Foresight for Generic UI Representations

TL;DR

This paper introduces Textual Foresight, a novel pretraining method for UI representations that predicts future UI states from current screens, improving performance and data efficiency in UI tasks.

Contribution

It proposes a new pretraining objective for UI representations that jointly reasons over screen elements and overall layout, and introduces the OpenApp dataset for UI learning.

Findings

Outperforms state-of-the-art by 2% on generation tasks with 28x fewer images.

Improves average task performance by 5.7% over baselines.

First public dataset for app UI representation learning.

Abstract

Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current UI and local action taken. Our approach requires joint reasoning over elements and entire screens, resulting in improved UI features: on generation tasks, UI agents trained with Textual Foresight outperform state-of-the-art by 2% with 28x fewer images. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning. OpenApp enables new baselines, and we find Textual Foresight improves average task performance over them by 5.7% while having access to 2x less data.