{"url":"/task/chart-understanding","name":"Chart Understanding","slug":"chart-understanding","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":47,"papers_with_code":27,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/sbsfigures","name":"SBS Figures","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-question-answering","name":"Visual Question Answering (VQA)"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":27,"of":27,"tagged_in_all":47,"items":[{"url":"/paper/mmc-advancing-multimodal-chart-understanding","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","date":"2023-11-15","arxiv_id":"2311.10774","repositories_listed":6,"syntology":{"n":19,"n_ran":9,"n_unverified":10,"n_pointer_only":9}},{"url":"/paper/infochartqa-a-benchmark-for-multimodal","title":"InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts","date":"2025-05-25","arxiv_id":"2505.19028","repositories_listed":3,"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/chartgalaxy-a-dataset-for-infographic-chart","title":"ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation","date":"2025-05-24","arxiv_id":"2505.18668","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/orionbench-a-benchmark-for-chart-and-human","title":"OrionBench: A Benchmark for Chart and Human-Recognizable Object Detection in Infographics","date":"2025-05-23","arxiv_id":"2505.17473","repositories_listed":3,"syntology":null},{"url":"/paper/structchart-perception-structuring-reasoning","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","date":"2023-09-20","arxiv_id":"2309.11268","repositories_listed":3,"syntology":null},{"url":"/paper/chartsketcher-reasoning-with-multimodal","title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","date":"2025-05-25","arxiv_id":"2505.19076","repositories_listed":1,"syntology":null},{"url":"/paper/chartcards-a-chart-metadata-generation","title":"ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding","date":"2025-05-21","arxiv_id":"2505.15046","repositories_listed":1,"syntology":null},{"url":"/paper/chartedit-how-far-are-mllms-from-automating","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","date":"2025-05-17","arxiv_id":"2505.11935","repositories_listed":1,"syntology":null},{"url":"/paper/chartqapro-a-more-diverse-and-challenging","title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","date":"2025-04-07","arxiv_id":"2504.05506","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/refchartqa-grounding-visual-answer-on-chart","title":"RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning","date":"2025-03-29","arxiv_id":"2503.23131","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-perception-bottleneck-of-vlms-for","title":"On the Perception Bottleneck of VLMs for Chart Understanding","date":"2025-03-24","arxiv_id":"2503.18435","repositories_listed":1,"syntology":null},{"url":"/paper/chartcoder-advancing-multimodal-large","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","date":"2025-01-11","arxiv_id":"2501.06598","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/askchart-universal-chart-understanding","title":"AskChart: Universal Chart Understanding through Textual Enhancement","date":"2024-12-26","arxiv_id":"2412.19146","repositories_listed":1,"syntology":null},{"url":"/paper/sbs-figures-pre-training-figure-qa-from-stage","title":"SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images","date":"2024-12-23","arxiv_id":"2412.17606","repositories_listed":1,"syntology":null},{"url":"/paper/deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/evochart-a-benchmark-and-a-self-training","title":"EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding","date":"2024-09-03","arxiv_id":"2409.01577","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-self-instruct-synthetic-abstract","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","date":"2024-07-09","arxiv_id":"2407.07053","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/chartgemma-visual-instruction-tuning-for","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","date":"2024-07-04","arxiv_id":"2407.04172","repositories_listed":1,"syntology":null},{"url":"/paper/charxiv-charting-gaps-in-realistic-chart","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","date":"2024-06-26","arxiv_id":"2406.18521","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tinychart-efficient-chart-understanding-with","title":"TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning","date":"2024-04-25","arxiv_id":"2404.16635","repositories_listed":1,"syntology":null},{"url":"/paper/from-pixels-to-insights-a-survey-on-automatic","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","date":"2024-03-18","arxiv_id":"2403.12027","repositories_listed":1,"syntology":null},{"url":"/paper/chartinstruct-instruction-tuning-for-chart","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","date":"2024-03-14","arxiv_id":"2403.09028","repositories_listed":1,"syntology":null},{"url":"/paper/improving-language-understanding-from","title":"Improving Language Understanding from Screenshots","date":"2024-02-21","arxiv_id":"2402.14073","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/vary-scaling-up-the-vision-vocabulary-for","title":"Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06109","repositories_listed":1,"syntology":null},{"url":"/paper/unichart-a-universal-vision-language","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","date":"2023-05-24","arxiv_id":"2305.14761","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/chartreader-a-unified-framework-for-chart","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","date":"2023-04-05","arxiv_id":"2304.02173","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_unverified":3,"n_pointer_only":19}},{"url":"/paper/dvqa-understanding-data-visualizations-via","title":"DVQA: Understanding Data Visualizations via Question Answering","date":"2018-01-24","arxiv_id":"1801.08163","repositories_listed":1,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}