{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/screenai-a-vision-language-model-for-ui-and","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","arxiv_id":"2402.04615","date":"2024-02-07","proceeding":null,"authors":["Gilles Baechler","Srinivas Sunkara","Maria Wang","Fedir Zubach","Hassan Mansoor","Vincent Etter","Victor Cărbune","Jason Lin","Jindong Chen","Abhanshu Sharma"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2402.04615v3","url_pdf":"https://arxiv.org/pdf/2402.04615v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"screenai-a-vision-language-model-for-ui-and","repo_url":"https://github.com/google-research-datasets/screen_annotation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"screenai-a-vision-language-model-for-ui-and","repo_url":"https://github.com/google-research-datasets/screen_qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"chart-question-answering","task_name":"Chart Question Answering"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"patching","method_name":"Patching"}],"datasets_introduced":[{"slug":"screenqa-short","name":"ScreenQA Short","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"ScreenAI 5B (4.62 B params, w/ OCR)","rank_in_archive_order":6,"of":27,"metrics":{"1:1 Accuracy":"76.7"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"ScreenAI 5B (4.62 B params, w/OCR)","rank_in_archive_order":6,"of":33,"metrics":{"ANLS":"0.8988"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"ScreenAI 5B (4.62 B params, w/ OCR)","rank_in_archive_order":3,"of":21,"metrics":{"ANLS":"65.90"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.04615","atlas_url":"https://app.syntology.ai/?focus=2402.04615","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2402.04615"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.04615\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.04615"},"call":"get_concepts_for_paper(arxiv_id=\"2402.04615\")"}],"by_repo":[{"repo":"google-research-datasets/screen_annotation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"google-research-datasets/screen_qa","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2209.08199"],"harvested_for_calls":[{"arxiv_id":"2209.08199","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2209.08199"},"call":"get_harvested_code_for_paper(arxiv_id=\"2209.08199\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"479ffa25669c6a9a5f20e7bf70177b102a967dc760acdfdd6b15f4428b9f40ee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}