From pixels to insights: A survey on automatic chart understanding in the era of large foundation models

KH Huang, HP Chan, YR Fung, H Qiu… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
Data visualization in the form of charts plays a pivotal role in data analysis, offering critical
insights and aiding in informed decision-making. Automatic chart understanding has …

Tinychart: Efficient chart understanding with visual token merging and program-of-thoughts learning

L Zhang, A Hu, H Xu, M Yan, Y Xu, Q **… - arxiv preprint arxiv …, 2024 - arxiv.org
Charts are important for presenting and explaining complex data relationships. Recently,
multimodal large language models (MLLMs) have shown remarkable capabilities in various …

Chartbench: A benchmark for complex visual reasoning in charts

Z Xu, S Du, Y Qi, C Xu, C Yuan, J Guo - arxiv preprint arxiv:2312.15915, 2023 - arxiv.org
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in image
understanding and generation. However, current benchmarks fail to accurately evaluate the …

Chartmimic: Evaluating lmm's cross-modal reasoning capability via chart-to-code generation

C Shi, C Yang, Y Liu, B Shui, J Wang, M **g… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded
code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes …

Viseval: A benchmark for data visualization in the era of large language models

N Chen, Y Zhang, J Xu, K Ren… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Translating natural language to visualization (NL2VIS) has shown great promise for visual
data analysis, but it remains a challenging task that requires multiple low-level …

Advancing multimodal large language models in chart question answering with visualization-referenced instruction tuning

X Zeng, H Lin, Y Ye, W Zeng - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Emerging multimodal large language models (MLLMs) exhibit great potential for chart
question answering (CQA). Recent efforts primarily focus on scaling up training datasets (ie …

TinyChart: Efficient chart understanding with program-of-thoughts learning and visual token merging

L Zhang, A Hu, H Xu, M Yan, Y Xu, Q **… - Proceedings of the …, 2024 - aclanthology.org
Charts are important for presenting and explaining complex data relationships. Recently,
multimodal large language models (MLLMs) have shown remarkable capabilities in chart …