Papers › ScreenAI: A Vision-Language Model for UI and Infographics Understanding

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

7 Feb 2024arXiv:2402.04615archive 2025-07-28

Gilles Baechler, Srinivas Sunkara, Maria Wang, Fedir Zubach, Hassan Mansoor, Vincent Etter, Victor Cărbune, Jason Lin, Jindong Chen, Abhanshu Sharma

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. 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. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-artresults on UI- and infographics-based tasks (Multi-page DocVQA, WebSRC, MoTIF and Widget Captioning), and new best-in-class performance on others (Chart QA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research-datasets/screen_annotation officialmentioned in papermentioned on GitHub report
google-research-datasets/screen_qa officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Chart Question AnsweringLanguage ModelingLanguage ModellingQuestion AnsweringVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

ScreenQA Short

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chart Question Answering ChartQA ScreenAI 5B (4.62 B params, w/ OCR) 1:1 Accuracy 76.7 #6 of 27 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test ScreenAI 5B (4.62 B params, w/OCR) ANLS 0.8988 #6 of 33 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA ScreenAI 5B (4.62 B params, w/ OCR) ANLS 65.90 #3 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Patching

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections