Harnessing Webpage UIs for Text-Rich Visual Understanding

• URL: http://arxiv.org/abs/2410.13824v3
• Date: Wed, 06 Nov 2024 08:29:22 GMT
• Title: Harnessing Webpage UIs for Text-Rich Visual Understanding
• Authors: Junpeng Liu, Tianyue Ou, Yifan Song, Yuxiao Qu, Wai Lam, Chenyan Xiong, Wenhu Chen, Graham Neubig, Xiang Yue,
• Abstract summary: 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.
• Score: 112.01029887404296
• License:
• Abstract: Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To enhance this capability, we propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs). Despite lacking direct visual input, text-based LLMs are able to process structured text representations from webpage accessibility trees. 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. Models trained on MultiUI not only excel in web UI tasks-achieving up to a 48% improvement on VisualWebBench and a 19.1% boost in element accuracy on a web agent dataset Mind2Web-but also generalize surprisingly well to non-web UI tasks and even to non-UI domains, such as document understanding, OCR, and chart interpretation. These results highlight the broad applicability of web UI data for advancing text-rich visual understanding across various scenarios.

Related papers

• Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs [112.89665642941814]
  Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio. Current MLLMs are surprisingly poor at understanding webpage screenshots and generating their corresponding HTML code. We propose Web2Code, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:59:46Z)
• 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)
• Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want [58.091825321168514]
  We introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting. Specifically, we propose a new end-to-end trained Multimodal Large Language Model (MLLM) that connects a vision encoder, a visual prompt encoder and an LLM. To advance visual prompting research for MLLMs, we introduce MDVP-Data and MDVP-Bench.
  arXiv  Detail & Related papers  (2024-03-29T16:26:20Z)
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks [93.85005277463802]
  VisualWebArena is a benchmark designed to assess the performance of multimodal web agents on realistic tasks. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives.
  arXiv  Detail & Related papers  (2024-01-24T18:35:21Z)
• UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model [108.85584502396182]
  We propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters. Our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks.
  arXiv  Detail & Related papers  (2023-10-08T11:33:09Z)
• ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations [13.939350184164017]
  Multimodal Vision-Language Models (VLMs) enable powerful applications from their fused understanding of images and language. We adapt a recipe for generating paired text-image training data for VLMs to the UI domain by combining existing pixel-based methods with a Large Language Model (LLM) We generate a dataset of 335K conversational examples paired with UIs that cover Q&A, UI descriptions, and planning, and use it to fine-tune a conversational VLM for UI tasks.
  arXiv  Detail & Related papers  (2023-10-07T16:32:34Z)
• Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning [34.24671403624908]
  Mobile User Interface Summarization generates succinct language descriptions of mobile screens for conveying important contents and functionalities of the screen. We present Screen2Words, a novel screen summarization approach that automatically encapsulates essential information of a UI screen into a coherent language phrase.
  arXiv  Detail & Related papers  (2021-08-07T03:01:23Z)
• UIBert: Learning Generic Multimodal Representations for UI Understanding [12.931540149350633]
  We introduce a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy.
  arXiv  Detail & Related papers  (2021-07-29T03:51:36Z)
• ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces [12.52699475631247]
  We introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%.
  arXiv  Detail & Related papers  (2020-12-22T20:49:52Z)

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.