ShowUI: One Vision-Language-Action Model for GUI Visual Agent

• URL: http://arxiv.org/abs/2411.17465v1
• Date: Tue, 26 Nov 2024 14:29:47 GMT
• Title: ShowUI: One Vision-Language-Action Model for GUI Visual Agent
• Authors: Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Weixian Lei, Lijuan Wang, Mike Zheng Shou,
• Abstract summary: Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. We develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations. ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding.
• Score: 80.50062396585004
• License:
• Abstract: Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances. With above components, ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up the performance by 1.4x. Navigation experiments across web Mind2Web, mobile AITW, and online MiniWob environments further underscore the effectiveness and potential of our model in advancing GUI visual agents. The models are available at https://github.com/showlab/ShowUI.

Related papers

• Harnessing Webpage UIs for Text-Rich Visual Understanding [112.01029887404296]
  We propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs) These instructions are then paired with UI screenshots to train multimodal models. We introduce MultiUI, a dataset containing 7.3 million samples from 1 million websites, covering diverse multimodal tasks and UI layouts.
  arXiv  Detail & Related papers  (2024-10-17T17:48:54Z)
• Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents [20.08996257335876]
  We advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly take pixel-level operations on the GUI. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models.
  arXiv  Detail & Related papers  (2024-10-07T17:47:50Z)
• GUI Action Narrator: Where and When Did That Action Take Place? [19.344324166716245]
  We develop a video captioning benchmark for GUI actions, comprising 4,189 diverse video captioning samples. This task presents unique challenges compared to natural scene video captioning. We introduce our GUI action dataset textbfAct2Cap as well as a simple yet effective framework, textbfGUI Narrator, for GUI video captioning.
  arXiv  Detail & Related papers  (2024-06-19T17:22:11Z)
• GUICourse: From General Vision Language Models to Versatile GUI Agents [75.5150601913659]
  We contribute GUICourse, a suite of datasets to train visual-based GUI agents. First, we introduce the GUIEnv dataset to strengthen the OCR and grounding capabilities of VLMs. Then, we introduce the GUIAct and GUIChat datasets to enrich their knowledge of GUI components and interactions.
  arXiv  Detail & Related papers  (2024-06-17T08:30:55Z)
• GUI-WORLD: A Dataset for GUI-oriented Multimodal LLM-based Agents [73.9254861755974]
  This paper introduces a new dataset, called GUI-World, which features meticulously crafted Human-MLLM annotations. We evaluate the capabilities of current state-of-the-art MLLMs, including ImageLLMs and VideoLLMs, in understanding various types of GUI content.
  arXiv  Detail & Related papers  (2024-06-16T06:56:53Z)
• VideoGUI: A Benchmark for GUI Automation from Instructional Videos [78.97292966276706]
  VideoGUI is a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software. Our evaluation reveals that even the SoTA large multimodal model GPT4o performs poorly on visual-centric GUI tasks.
  arXiv  Detail & Related papers  (2024-06-14T17:59:08Z)
• Tell Me What's Next: Textual Foresight for Generic UI Representations [65.10591722192609]
  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. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning.
  arXiv  Detail & Related papers  (2024-06-12T02:43:19Z)
• Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces [27.84098739594353]
  Graph4GUI exploits graph neural networks to capture individual elements' properties and semantic-visuo-spatial constraints in a layout. The learned representation demonstrated its effectiveness in multiple tasks, especially generating designs in a challenging GUI autocompletion task.
  arXiv  Detail & Related papers  (2024-04-21T04:06:09Z)
• ScreenAI: A Vision-Language Model for UI and Infographics Understanding [4.914575630736291]
  We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale.
  arXiv  Detail & Related papers  (2024-02-07T06:42:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.