{"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/matcha-enhancing-visual-language-pretraining","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","arxiv_id":"2212.09662","date":"2022-12-19","proceeding":null,"authors":["Fangyu Liu","Francesco Piccinno","Syrine Krichene","Chenxi Pang","Kenton Lee","Mandar Joshi","Yasemin Altun","Nigel Collier","Julian Martin Eisenschlos"],"abstract":"Visual language data such as plots, charts, and infographics are ubiquitous in the human world. However, state-of-the-art vision-language models do not perform well on these data. We propose MatCha (Math reasoning and Chart derendering pretraining) to enhance visual language models' capabilities in jointly modeling charts/plots and language data. Specifically, we propose several pretraining tasks that cover plot deconstruction and numerical reasoning which are the key capabilities in visual language modeling. We perform the MatCha pretraining starting from Pix2Struct, a recently proposed image-to-text visual language model. On standard benchmarks such as PlotQA and ChartQA, the MatCha model outperforms state-of-the-art methods by as much as nearly 20%. We also examine how well MatCha pretraining transfers to domains such as screenshots, textbook diagrams, and document figures and observe overall improvement, verifying the usefulness of MatCha pretraining on broader visual language tasks.","url_abs":"https://arxiv.org/abs/2212.09662v2","url_pdf":"https://arxiv.org/pdf/2212.09662v2.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":"matcha-enhancing-visual-language-pretraining","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chart-question-answering","task_name":"Chart Question Answering"},{"task_slug":"data-summarization","task_name":"Data Summarization"},{"task_slug":"derendering","task_name":"Derendering"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"math","task_name":"Math"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"MatCha","rank_in_archive_order":21,"of":27,"metrics":{"1:1 Accuracy":"64.2"},"uses_additional_data":false},{"leaderboard":"/sota/chart-question-answering-on-plotqa","task":"Chart Question Answering","dataset":"PlotQA","model":"MatCha","rank_in_archive_order":2,"of":6,"metrics":{"1:1 Accuracy":"91.5"},"uses_additional_data":false},{"leaderboard":"/sota/chart-question-answering-on-realcqa","task":"Chart Question Answering","dataset":"RealCQA","model":"Matcha-chartQA","rank_in_archive_order":4,"of":5,"metrics":{"1:1 Accuracy":"0.259728175283818"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d1-1","task":"Visual Question Answering","dataset":"PlotQA-D1","model":"MatCha","rank_in_archive_order":2,"of":2,"metrics":{"1:1 Accuracy":"92.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d2-1","task":"Visual Question Answering","dataset":"PlotQA-D2","model":"MatCha","rank_in_archive_order":2,"of":2,"metrics":{"1:1 Accuracy":"90.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"MatCha","rank_in_archive_order":27,"of":33,"metrics":{"ANLS":"0.742"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"MatCha","rank_in_archive_order":20,"of":21,"metrics":{"ANLS":"37.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.09662","atlas_url":"https://app.syntology.ai/?focus=2212.09662","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":"2212.09662"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.09662\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.09662"},"call":"get_concepts_for_paper(arxiv_id=\"2212.09662\")"}],"by_repo":[{"repo":"huggingface/transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1910.03771","2006.03654","2010.01057"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1910.03771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03771"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03771\")"},{"arxiv_id":"2006.03654","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.03654"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.03654\")"},{"arxiv_id":"2010.01057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01057\")"}]}],"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":"a7f19802b6707c151e3395047e9028928f1ee0a5e6a3279b8c3c86a251f07b8b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}