AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

Renqiu Xia, Haoyang Peng, Hancheng Ye, Mingsheng Li, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan, Bo Zhang

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 64 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 9K simulated charts (SimChart9K) to ChartQA training (ablation)StructChart · ChartQA val (strict)mPrecision: 0.6770 -> 0.7116Improved
scale simulated data from 0.1K to 9K (ablation)StructChart · ChartQA val (high tolerance)mPrecision: 0.8326 -> 0.8527Improved
add SimChart9K to real merged training data (ablation)StructChart · PlotQA val (strict)mPrecision: 0.4549 -> 0.4596Improved
add SimChart9K to real merged training data (ablation)StructChart · Chart2Text val (strict)mPrecision: 0.3156 -> 0.3394Improved
add SimChart9K to real merged training data (ablation)StructChart · ChartQA val (high tolerance)mPrecision: 0.8591 -> 0.8568No clear effect
merge ChartQA, PlotQA and Chart2Text training sets (ablation)StructChart · PlotQA val (strict)mPrecision: 0.1995 -> 0.4549Improved
use STR instead of LCT as intermediate representation (ablation)StructChart+Llama3.1-8b · ChartQA testrelaxed accuracy (avg): 55.7 -> 66.4Improved
use STR instead of LCT as intermediate representation (ablation)StructChart+Vicuna-13b · ChartQA testrelaxed accuracy (avg): 50.2 -> 59.3Improved
use STR instead of LCT as intermediate representation (ablation)StructChart+GPT-4 · ChartQA testrelaxed accuracy (avg): 76.8 -> 78.5Improved
use STR instead of LCT as intermediate representation (ablation)StructChart+Llama3.1-70b · ChartQA testrelaxed accuracy (avg): 74.3 -> 75.4Improved
two-stage StructChart+GPT-4 vs end-to-end GPT-4VStructChart+GPT-4 · ChartQA testrelaxed accuracy (avg): 75.5 -> 78.5Improved
use only simulated data without real charts (zero-shot) (ablation)StructChart · ChartQA valmPrecisionHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy