Papers with SOTA closed-source VLMs
Is GPT-4V (ision) All You Need for Automating Academic Data Visualization? Exploring Vision-Language Models’ Capability in Reproducing Academic Charts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Using Vision-Language Models (VLMs) for data visualizations requires significant time and expertise in both data management and graphic design. |
| Approach: | They propose a dataset comprising 2525 high-resolution data visualization figures with captions from AI conferences, extracted directly from source codes. |
| Outcome: | The proposed model outperforms open-source models in reproducing complex charts while using Chain-of-Thought prompting. |