# Lexi: Self-Supervised Learning of the UI Language

arXiv: https://arxiv.org/abs/2301.10165 · HTML: https://mlsanity.com/paper/2301.10165/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 54 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Mapping Natural Language Instructions to Mobile UI Action Sequences](https://mlsanity.com/paper/2005.03776/) (2020)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data](https://mlsanity.com/paper/2001.07966/) (2020)
- [Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements](https://mlsanity.com/paper/2010.04295/) (2020)
- [UIBert: Learning Generic Multimodal Representations for UI Understanding](https://mlsanity.com/paper/2107.13731/) (2021)
- [RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes](https://mlsanity.com/paper/1809.00812/) (2018)
- [Learning to Navigate the Web](https://mlsanity.com/paper/1812.09195/) (2018)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces](https://mlsanity.com/paper/2012.12350/) (2020)
- [Learning to Win by Reading Manuals in a Monte-Carlo Framework](https://mlsanity.com/paper/1401.5390/) (2014)
- [Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps](https://mlsanity.com/paper/1802.02312/) (2018)
- [Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?](https://mlsanity.com/paper/2008.05132/) (2020)
- [Unblind Your Apps: Predicting Natural-Language Labels for Mobile GUI Components by Deep Learning](https://mlsanity.com/paper/2003.00380/) (2020)
- [Mapping Natural Language Commands to Web Elements](https://mlsanity.com/paper/1808.09132/) (2018)

## Built on by (most cited first, 10 of 10)

- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web](https://mlsanity.com/paper/2402.17553/) (2024)
- [A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models](https://mlsanity.com/paper/2503.23350/) (2025)
- [DroidBot-GPT: GPT-powered UI Automation for Android](https://mlsanity.com/paper/2304.07061/) (2023)
- [ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation](https://mlsanity.com/paper/2312.13108/) (2023)
- [VideoGUI: A Benchmark for GUI Automation from Instructional Videos](https://mlsanity.com/paper/2406.10227/) (2024)
- [UINav: A Practical Approach to Train On-Device Automation Agents](https://mlsanity.com/paper/2312.10170/) (2023)
- [Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents](https://mlsanity.com/paper/2410.18529/) (2024)

## Abstract (arXiv)

Humans can learn to operate the user interface (UI) of an application by reading an instruction manual or how-to guide. Along with text, these resources include visual content such as UI screenshots and images of application icons referenced in the text. We explore how to leverage this data to learn generic visio-linguistic representations of UI screens and their components. These representations are useful in many real applications, such as accessibility, voice navigation, and task automation. Prior UI representation models rely on UI metadata (UI trees and accessibility labels), which is often missing, incompletely defined, or not accessible. We avoid such a dependency, and propose Lexi, a pre-trained vision and language model designed to handle the unique features of UI screens, including their text richness and context sensitivity. To train Lexi we curate the UICaption dataset consisting of 114k UI images paired with descriptions of their functionality. We evaluate Lexi on four tasks: UI action entailment, instruction-based UI image retrieval, grounding referring expressions, and UI entity recognition.