Papers › MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Fangyu Liu, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Yasemin Altun, Nigel Collier, Julian Martin Eisenschlos
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Chart Question Answering | ChartQA | MatCha | 1:1 Accuracy | 64.2 | #21 of 27 | Archive leaderboard | report |
| Chart Question Answering | PlotQA | MatCha | 1:1 Accuracy | 91.5 | #2 of 6 | Archive leaderboard | report |
| Chart Question Answering | RealCQA | Matcha-chartQA | 1:1 Accuracy | 0.259728175283818 | #4 of 5 | Archive leaderboard | report |
| Visual Question Answering | PlotQA-D1 | MatCha | 1:1 Accuracy | 92.3 | #2 of 2 | Archive leaderboard | report |
| Visual Question Answering | PlotQA-D2 | MatCha | 1:1 Accuracy | 90.7 | #2 of 2 | Archive leaderboard | report |
| Visual Question Answering (VQA) | DocVQA test | MatCha | ANLS | 0.742 | #27 of 33 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfographicVQA | MatCha | ANLS | 37.2 | #20 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.
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