ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K question-answer pairs collected by human annotators for ~35K screenshots from Rico. It should be used to train and evaluate models capable of screen content understanding via question answering.
☆139Feb 7, 2025Updated last year
Alternatives and similar repositories for screen_qa
Users that are interested in screen_qa are comparing it to the libraries listed below
Sorting:
- The Screen Annotation dataset consists of pairs of mobile screenshots and their annotations. The annotations are in text format, and desc…☆84Mar 7, 2024Updated last year
- Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments☆61Aug 19, 2024Updated last year
- ☆33Oct 1, 2024Updated last year
- The model, data and code for the visual GUI Agent SeeClick☆467Jul 13, 2025Updated 7 months ago
- GUICourse: From General Vision Langauge Models to Versatile GUI Agents☆136Updated this week
- It includes two datasets that are used in the downstream tasks for evaluating UIBert: App Similar Element Retrieval data and Visual Item …☆47Aug 2, 2021Updated 4 years ago
- Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"☆378Feb 6, 2026Updated 3 weeks ago
- Official implementation for "Android in the Zoo: Chain-of-Action-Thought for GUI Agents" (Findings of EMNLP 2024)☆99Oct 14, 2024Updated last year
- The dataset includes screen summaries that describes Android app screenshot's functionalities. It is used for training and evaluation of …☆63Jul 27, 2021Updated 4 years ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆300Jul 18, 2025Updated 7 months ago
- VisionDroid☆21Apr 2, 2024Updated last year
- ☆20Apr 24, 2024Updated last year
- The dataset includes widget captions that describes UI element's functionalities. It is used for training and evaluation of the widget ca…☆23Jun 24, 2021Updated 4 years ago
- (ICLR 2025) The Official Code Repository for GUI-World.☆68Dec 18, 2024Updated last year
- A mobile GUI search engine using a vision-language model☆14May 5, 2025Updated 9 months ago
- A React Native module to access ReplayKit screen recording framework on iOS☆13Jan 3, 2023Updated 3 years ago
- https://github.com/bernakabadayi/ganavatar☆12Oct 8, 2024Updated last year
- Evaluation code for Ref-L4, a new REC benchmark in the LMM era☆57Dec 28, 2024Updated last year
- Collection of Aesthetics Assessment Papers for Graphic Designs.☆35Aug 29, 2025Updated 6 months ago
- GUI Grounding for Professional High-Resolution Computer Use☆333Feb 20, 2026Updated last week
- ☆31Sep 27, 2024Updated last year
- ☆17Jun 12, 2024Updated last year
- This repository contains the opensource version of the datasets were used for different parts of training and testing of models that grou…☆34Aug 20, 2020Updated 5 years ago
- ☆30Dec 27, 2024Updated last year
- Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?☆128Feb 20, 2024Updated 2 years ago
- Web-grounded natural language instructions☆18Nov 25, 2024Updated last year
- ☆19Sep 11, 2024Updated last year
- Custom object detection for UI of the design system using TensorFlow☆16Jun 20, 2023Updated 2 years ago
- ☆680Jun 3, 2025Updated 9 months ago
- A tidied repo for UI2CODE, a reverse engineering system convert UI design to code automatically and precisely.☆44Jan 6, 2021Updated 5 years ago
- ☆239Apr 18, 2025Updated 10 months ago
- This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.or…☆161Sep 27, 2025Updated 5 months ago
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆437Apr 20, 2025Updated 10 months ago
- convert equation inside word(.docx) to latex☆24Oct 17, 2025Updated 4 months ago
- On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)☆796Jul 5, 2025Updated 7 months ago
- The dataset includes UI object type labels (e.g., BUTTON, IMAGE, CHECKBOX) that describes the semantic type of an UI object on Android ap…☆53Jan 14, 2022Updated 4 years ago
- A Universal Platform for Training and Evaluation of Mobile Interaction☆60Sep 24, 2025Updated 5 months ago
- [NeurIPS 2025] UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents☆53Nov 27, 2025Updated 3 months ago
- Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"☆64Oct 19, 2024Updated last year