OpusAnimation: Code-Based Dynamic Chart Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912626816057344 |
|---|---|
| author | Li, Bozheng Yang, Miao Chen, Zhenhan Cao, Jiawang Liu, Mushui Lu, Yi Wu, Yongliang Zhang, Bin Ji, Yangguang Tang, Licheng Wu, Jay Zhu, Wenbo |
| author_facet | Li, Bozheng Yang, Miao Chen, Zhenhan Cao, Jiawang Liu, Mushui Lu, Yi Wu, Yongliang Zhang, Bin Ji, Yangguang Tang, Licheng Wu, Jay Zhu, Wenbo |
| contents | Dynamic Chart Generation (DCG) involves producing code-rendered animated visualizations as charts. While recent advances in multi-modal large language models (MLLMs) have significantly improved their capability on static chart generation and comprehension, MLLMs' potential for handling dynamic chart generation and understanding remains underexplored. To bridge this research gap, we introduce DCG-Bench (Dynamic Chart Generation Benchmark), the first benchmark evaluating MLLM's capability on dynamic chart generation tasks from three dimensions: Simple Text-to-Chart, Detailed Text-to-Chart, and Video-to-Chart tasks. We construct DCG-8K, a high-quality DCG dataset with annotations covering instruction-code-video triplets and QA pairs for both code and video evaluation. Based on DCG-8K, we explored a two-stage training recipe, proposing Joint-Code-Visual Reward for group relative policy optimization to construct expert MLLM Qwen2.5-VL-DCG-3B for the DCG task. Our benchmarking result reveals shortcomings of existing MLLMs in the visual-to-chart task, and our model beats the best open-sourced MLLM with an average 8.31% performance gain across three tasks, and shows on par performance against proprietary models with only 3B parameters, proving the effectiveness of our training recipe. Our code and dataset will be publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03341 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpusAnimation: Code-Based Dynamic Chart Generation Li, Bozheng Yang, Miao Chen, Zhenhan Cao, Jiawang Liu, Mushui Lu, Yi Wu, Yongliang Zhang, Bin Ji, Yangguang Tang, Licheng Wu, Jay Zhu, Wenbo Computer Vision and Pattern Recognition Dynamic Chart Generation (DCG) involves producing code-rendered animated visualizations as charts. While recent advances in multi-modal large language models (MLLMs) have significantly improved their capability on static chart generation and comprehension, MLLMs' potential for handling dynamic chart generation and understanding remains underexplored. To bridge this research gap, we introduce DCG-Bench (Dynamic Chart Generation Benchmark), the first benchmark evaluating MLLM's capability on dynamic chart generation tasks from three dimensions: Simple Text-to-Chart, Detailed Text-to-Chart, and Video-to-Chart tasks. We construct DCG-8K, a high-quality DCG dataset with annotations covering instruction-code-video triplets and QA pairs for both code and video evaluation. Based on DCG-8K, we explored a two-stage training recipe, proposing Joint-Code-Visual Reward for group relative policy optimization to construct expert MLLM Qwen2.5-VL-DCG-3B for the DCG task. Our benchmarking result reveals shortcomings of existing MLLMs in the visual-to-chart task, and our model beats the best open-sourced MLLM with an average 8.31% performance gain across three tasks, and shows on par performance against proprietary models with only 3B parameters, proving the effectiveness of our training recipe. Our code and dataset will be publicly available. |
| title | OpusAnimation: Code-Based Dynamic Chart Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.03341 |