A curated list of recent and past chart understanding work based on our IEEE TKDE survey paper: From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models.
Official PyTorch implementation for ״ lassification-Regression for Chart Comprehension״
Officical repository for the paper“ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering”(EMNLP'24)
Code and datasets accompanying the ACL 2026 Main conference paper: "Protecting multimodal large language models against misleading visualizations"
Chart VQA is an intelligent chart question-answering system designed to help users understand information presented in charts and graphs. The project combines computer vision, optical character recognition, and vision-language models to analyze an uploaded chart and answer questions about its content in Vietnamese or English.
Build pipeline, decontamination audit and a 16-check verifier for scientific-chart-qa-17k: 17,070 evidence-grounded chart questions with a 14.5% unanswerable slice.
Reproducible VLM benchmark for provenance reward misspecification and online RL.
To associate your repository with the chart-question-answering topic, visit your repo's landing page and select "manage topics."