paper-with-me

홈 › Papers

Android in the Wild: A Large-Scale Dataset for Android Device Control

2023-07-19 · Christopher Rawles, Alice Li, Daniel Rodriguez, Oriana Riva, Timothy Lillicrap

There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user interface. We present a dataset for device-control research, Android in the Wild (AITW), which is orders of magnitude larger than current datasets. The dataset contains human demonstrations of device interactions, including the screens and actions, and corresponding natural language instructions. It consists of 715k episodes spanning 30k unique instructions, four versions of Android (v10-13),and eight device types (Pixel 2 XL to Pixel 6) with varying screen resolutions. It contains multi-step tasks that require semantic understanding of language and visual context. This dataset poses a new challenge: actions available through the user interface must be inferred from their visual appearance. And, instead of simple UI element-based actions, the action space consists of precise gestures (e.g., horizontal scrolls to operate carousel widgets). We organize our dataset to encourage robustness analysis of device-control systems, i.e., how well a system performs in the presence of new task descriptions, new applications, or new platform versions. We develop two agents and report performance across the dataset. The dataset is available at https://github.com/google-research/google-research/tree/master/android_in_the_wild.

📄 PDF Abstract BibTeX arXiv:2307.10088

Code (4)

google-research/google-research 공식 구현 tf
alipay/mobile-agent jax
digirl-agent/digirl pytorch
llamatouch/llamatouch

Similar Papers 제목 키워드 기반

AndroidInTheWild: A Large-Scale Dataset For Android Device Control

2023-09-26 · NeurIPS 2023 11

There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user interface. We present a dataset for devic…

A New Android Malware Detection Approach Using Bayesian Classification

2016-08-02 · Suleiman Y. Yerima, Sakir Sezer, Gavin McWilliams, Igor Muttik

Mobile malware has been growing in scale and complexity as smartphone usage continues to rise. Android has surpassed other mobile platforms as the most popular whilst also witnessing a dramatic increase in malware target…

Android Malware DetectionClassificationGeneral ClassificationMalware Detection

A3: Android Agent Arena for Mobile GUI Agents

2025-01-02 · Yuxiang Chai, Hanhao Li, Jiayu Zhang, Liang Liu 외

AI agents have become increasingly prevalent in recent years, driven by significant advancements in the field of large language models (LLMs). Mobile GUI agents, a subset of AI agents, are designed to autonomously perfor…

Information Retrieval

Context-aware, Adaptive and Scalable Android Malware Detection through Online Learning (extended version)

2017-06-03 · Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu

It is well-known that Android malware constantly evolves so as to evade detection. This causes the entire malware population to be non-stationary. Contrary to this fact, most of the prior works on Machine Learning based …

Android Malware DetectionMalware Detection

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents

2024-10-31 · Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng 외

Autonomous agents have become increasingly important for interacting with the real world. Android agents, in particular, have been recently a frequently-mentioned interaction method. However, existing studies for trainin…

Benchmarking