---
title: "ChartCoder — paper by Zhao et al. (2025) — summary and ideas"
description: "They present ChartCoder, a 7B MLLM built specifically for chart-to-code generation. 44 references, cited by 20 papers here."
authors: ["Xuanle Zhao", "Xianzhen Luo", "Qi Shi", "Chi Chen", "Shuo Wang", "Zhiyuan Liu", "Maosong Sun"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.363/"
doi: "10.18653/v1/2025.acl-long.363"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhao-2025-chartcoder-advancing-multimodal-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhao-2025-chartcoder-advancing-multimodal-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

# ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

**Authors:** [Xuanle Zhao](https://md.research.elamur.ai/free/en/authors/xuanle-zhao/), [Xianzhen Luo](https://md.research.elamur.ai/free/en/authors/xianzhen-luo/), Qi Shi, [Chi Chen](https://md.research.elamur.ai/free/en/authors/chi-chen/), [Shuo Wang](https://md.research.elamur.ai/free/en/authors/shuo-wang/), [Zhiyuan Liu](https://md.research.elamur.ai/free/en/authors/zhiyuan-liu/) and [Maosong Sun](https://md.research.elamur.ai/free/en/authors/maosong-sun/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.363/) · [PDF](https://aclanthology.org/2025.acl-long.363.pdf) · [DOI 10.18653/v1/2025.acl-long.363](https://doi.org/10.18653/v1/2025.acl-long.363) · [OpenAlex](https://openalex.org/W4412945598)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [20](https://md.research.elamur.ai/free/en/papers/zhao-2025-chartcoder-advancing-multimodal-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Open-source multimodal LLMs read charts reasonably well, but they struggle to turn a chart image into plotting code. Their output often fails to run, picks the wrong chart type, or loses details such as axis sizes. The authors argue that code is a lossless description of a chart, unlike textual summaries.

They present ChartCoder, a 7B MLLM built specifically for chart-to-code generation. It uses a Code LLM as its language backbone and is trained in two stages: chart–text alignment, then chart-to-code instruction tuning. Because suitable training data was scarce, they built Chart2Code-160k. To create it, an LLM first wrote Matplotlib/Seaborn programs with the data embedded directly in the code. These programs were executed to render charts, and faulty outputs were filtered out. The Snippet-of-Thought (SoT) method then rewrites part of the data as step-by-step generation that highlights key details like chart type, colors and values.

ChartCoder beats all open-source MLLMs on chart-to-code benchmarks in both executability and visual fidelity. This shows that a dedicated backbone and dedicated data matter for the task.

## Key points
- Chart2Code-160k contains 160k \<chart, instruction, code> pairs covering 27 chart types. About 200k LLM-generated snippets were guided by 79 hand-written template programs, then filtered down to the final set.
- SoT step-by-step data was produced from 50k sampled pairs. Removing this data noticeably hurt low- and high-level similarity scores, especially for text content and data values.
- Ablations show the Code LLM backbone raises the execution rate and cuts syntax and type errors. Swapping SigLIP-384 for CLIP-336 mainly lowers high-level similarity, an effect softened by an Any Resolution strategy.
- Evaluation covers chart-to-code benchmarks such as ChartMimic, Plot2Code and ChartX. Fine-tuning Qwen2-VL-7B on Chart2Code-160k also improved all metrics.
- Adding code as extra context on the MMC True/False task improved accuracy for both models tested:
  - MiniCPM-Llama3-V2.5: 0.76 → 0.81
  - InternVL2-8B: 0.79 → 0.82

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 333 works · 87,019 citations
- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 158 works · 28,841 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works · [💻 Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · 129 works

## Cite

Cite as: Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu and Maosong Sun. 2025. ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhao2025chartcoder,
  title = {{ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation}},
  author = {Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu and Maosong Sun},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.363},
  url = {https://doi.org/10.18653/v1/2025.acl-long.363}
}
```

- [← previous Baichuan-M1: Pushing the Medical Capability of Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2025-baichuan-m1-pushing-medical/)
- [next → Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance](https://md.research.elamur.ai/free/en/papers/pecher-2025-comparing-specialised-small-general-large/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

44 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2024. Introducing the next generation of claude. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+Introducing+the+next+generation+of+claude%2E)
2. DeepSeek-AI Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, Huazuo Gao, Kaige Gao, Wenjun Gao, Ruiqi Ge, Kang Guan, Daya Guo, Jianzhong Guo, Guangbo Hao, Zhewen Hao, Ying He, Wen-Hui Hu, Panpan Huang, Erhang Li, Guowei Li, Jiashi… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI+Xiao+Bi%2C+Deli+Chen%2C+Guanting+Chen%2C+Shanhuang+Chen%2C+Damai+Dai%2C+Chengqi+Deng%2C+Honghui+Ding%2C+Kai+Dong%2C+Qiushi+Du%2C+Zhe+Fu%2C+Huazuo+Gao%2C+Kaige+Gao%2C+Wenjun+Gao%2C+Ruiqi+Ge%2C+Kang+Guan%2C+Daya+Guo%2C+Jia)
3. Ting-Yao Hsu, C Lee Giles, and Ting-Hao’Kenneth’ Huang. 2021. Scicap: Generating captions for scientific figures. arXiv preprint arXiv:2110.11624. [find](https://scholar.google.com/scholar?q=Ting%2DYao+Hsu%2C+C+Lee+Giles%2C+and+Ting%2DHao%E2%80%99Kenneth%E2%80%99+Huang%2E+2021%2E+Scicap%3A+Generating+captions+for+scientific+figures%2E+arXiv+preprint+arXiv%3A2110%2E11624%2E)
4. Shankar Kantharaj, Rixie Tiffany Ko Leong, Xiang Lin, Ahmed Masry, Megh Thakkar, Enamul Hoque, and Shafiq Joty. 2022. [Chart-to-text: A large-scale benchmark for chart summarization](https://md.research.elamur.ai/free/en/papers/kantharaj-2022-chart-text-large-scale-benchmark/). arXiv preprint arXiv:2203.06486.
5. Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024a. Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895. [find](https://scholar.google.com/scholar?q=Feng+Li%2C+Renrui+Zhang%2C+Hao+Zhang%2C+Yuanhan+Zhang%2C+Bo+Li%2C+Wei+Li%2C+Zejun+Ma%2C+and+Chunyuan+Li%2E+2024a%2E+Llava%2Dnext%2Dinterleave%3A+Tackling+multi%2Dimage%2C+video%2C+and+3d+in+large+multimodal+models%2E+arXiv+preprint+)
6. Kaixin Li, Yuchen Tian, Qisheng Hu, Ziyang Luo, Zhiyong Huang, and Jing Ma. 2024b. Mmcode: Benchmarking multimodal large language models for code generation with visually rich programming problems. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 736–783. [find](https://scholar.google.com/scholar?q=Kaixin+Li%2C+Yuchen+Tian%2C+Qisheng+Hu%2C+Ziyang+Luo%2C+Zhiyong+Huang%2C+and+Jing+Ma%2E+2024b%2E+Mmcode%3A+Benchmarking+multimodal+large+language+models+for+code+generation+with+visually+rich+programming+problems%2E+In)
7. Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, and Dong Yu. 2023a. [Mmc: Advancing multimodal chart understanding with large-scale instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2024-mmc-advancing-multimodal-chart-understanding/). arXiv preprint arXiv:2311.10774.
8. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023b. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/).
9. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024. Llava-next: Improved reasoning, ocr, and world knowledge. [find](https://scholar.google.com/scholar?q=Haotian+Liu%2C+Chunyuan+Li%2C+Yuheng+Li%2C+Bo+Li%2C+Yuanhan+Zhang%2C+Sheng+Shen%2C+and+Yong+Jae+Lee%2E+2024%2E+Llava%2Dnext%3A+Improved+reasoning%2C+ocr%2C+and+world+knowledge%2E)
10. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023c. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/).
11. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, et al. 2024. [Deepseek-vl: towards real-world vision-language understanding](https://md.research.elamur.ai/free/en/papers/lu-2024-deepseek-vl-real-world/). arXiv preprint arXiv:2403.05525.
12. Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Libo Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, and Wanxiang Che. 2024. Python is not always the best choice: Embracing multilingual program of thoughts. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7185–72… [find](https://scholar.google.com/scholar?q=Xianzhen+Luo%2C+Qingfu+Zhu%2C+Zhiming+Zhang%2C+Libo+Qin%2C+Xuanyu+Zhang%2C+Qing+Yang%2C+Dongliang+Xu%2C+and+Wanxiang+Che%2E+2024%2E+Python+is+not+always+the+best+choice%3A+Embracing+multilingual+program+of+thoughts%2E+In+P)
13. Ahmed Masry, Parsa Kavehzadeh, Xuan Long Do, Enamul Hoque, and Shafiq Joty. 2023. [Unichart: A universal vision-language pretrained model for chart comprehension and reasoning](https://md.research.elamur.ai/free/en/papers/masry-2023-unichart-universal-vision-language-pretrained/). arXiv preprint arXiv:2305.14761.
14. Fanqing Meng, Wenqi Shao, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, and Ping Luo. 2024. Chartassisstant: A universal chart multimodal language model via chart-to-table pre-training and multitask instruction tuning. arXiv preprint arXiv:2401.02384. — [arXiv:2401.02384](https://arxiv.org/abs/2401.02384) [find](https://scholar.google.com/scholar?q=Fanqing+Meng%2C+Wenqi+Shao%2C+Quanfeng+Lu%2C+Peng+Gao%2C+Kaipeng+Zhang%2C+Yu+Qiao%2C+and+Ping+Luo%2E+2024%2E+Chartassisstant%3A+A+universal+chart+multimodal+language+model+via+chart%2Dto%2Dtable+pre%2Dtraining+and+multitask+)
15. Nitesh Methani, Pritha Ganguly, Mitesh M Khapra, and Pratyush Kumar. 2020. Plotqa: Reasoning over scientific plots. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1527–1536. [find](https://scholar.google.com/scholar?q=Nitesh+Methani%2C+Pritha+Ganguly%2C+Mitesh+M+Khapra%2C+and+Pratyush+Kumar%2E+2020%2E+Plotqa%3A+Reasoning+over+scientific+plots%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision%2C)
16. OpenAI. 2023. Gpt-4v(ision) system card. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2023%2E+Gpt%2D4v%28ision%29+system+card%2E)
17. OpenAI. 2024. Gpt-4o. Accessed: 2024-05-13. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Gpt%2D4o%2E+Accessed%3A+2024%2D05%2D13%2E)
18. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
19. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8763. PM…
20. Chufan Shi, Cheng Yang, Yaxin Liu, Bo Shui, Junjie Wang, Mohan Jing, Linran Xu, Xinyu Zhu, Siheng Li, Yuxiang Zhang, et al. 2024. Chartmimic: Evaluating lmm’s cross-modal reasoning capability via chart-to-code generation. arXiv preprint arXiv:2406.09961. — [arXiv:2406.09961](https://arxiv.org/abs/2406.09961) [find](https://scholar.google.com/scholar?q=Chufan+Shi%2C+Cheng+Yang%2C+Yaxin+Liu%2C+Bo+Shui%2C+Junjie+Wang%2C+Mohan+Jing%2C+Linran+Xu%2C+Xinyu+Zhu%2C+Siheng+Li%2C+Yuxiang+Zhang%2C+et+al%2E+2024%2E+Chartmimic%3A+Evaluating+lmm%E2%80%99s+cross%2Dmodal+reasoning+capability+via+char)
21. Chenglei Si, Yanzhe Zhang, Zhengyuan Yang, Ruibo Liu, and Diyi Yang. 2024. Design2code: How far are we from automating front-end engineering? arXiv preprint arXiv:2403.03163. — [arXiv:2403.03163](https://arxiv.org/abs/2403.03163) [find](https://scholar.google.com/scholar?q=Chenglei+Si%2C+Yanzhe+Zhang%2C+Zhengyuan+Yang%2C+Ruibo+Liu%2C+and+Diyi+Yang%2E+2024%2E+Design2code%3A+How+far+are+we+from+automating+front%2Dend+engineering%3F+arXiv+preprint+arXiv%3A2403%2E03163%2E+%E2%80%94+%5BarXiv%3A2403%2E03163%5D%28http)
22. Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8317–8326. [find](https://scholar.google.com/scholar?q=Amanpreet+Singh%2C+Vivek+Natarajan%2C+Meet+Shah%2C+Yu+Jiang%2C+Xinlei+Chen%2C+Dhruv+Batra%2C+Devi+Parikh%2C+and+Marcus+Rohrbach%2E+2019%2E+Towards+vqa+models+that+can+read%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+)
23. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. 2023. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805.
24. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. 2024a. [Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution](https://md.research.elamur.ai/free/en/papers/wang-2024-qwen2-vl-enhancing-vision/). arXiv preprint arXiv:2409.12191.
25. Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024b. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Wenhai+Wang%2C+Zhe+Chen%2C+Xiaokang+Chen%2C+Jiannan+Wu%2C+Xizhou+Zhu%2C+Gang+Zeng%2C+Ping+Luo%2C+Tong+Lu%2C+Jie+Zhou%2C+Yu+Qiao%2C+et+al%2E+2024b%2E+Visionllm%3A+Large+language+model+is+also+an+open%2Dended+decoder+for+vision%2Dce)
26. Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, et al. 2024c. Charxiv: Charting gaps in realistic chart understanding in multimodal llms. arXiv preprint arXiv:2406.18521. [find](https://scholar.google.com/scholar?q=Zirui+Wang%2C+Mengzhou+Xia%2C+Luxi+He%2C+Howard+Chen%2C+Yitao+Liu%2C+Richard+Zhu%2C+Kaiqu+Liang%2C+Xindi+Wu%2C+Haotian+Liu%2C+Sadhika+Malladi%2C+et+al%2E+2024c%2E+Charxiv%3A+Charting+gaps+in+realistic+chart+understanding+in+mu)
27. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824–24837.
28. Chengyue Wu, Yixiao Ge, Qiushan Guo, Jiahao Wang, Zhixuan Liang, Zeyu Lu, Ying Shan, and Ping Luo. 2024. Plot2code: A comprehensive benchmark for evaluating multi-modal large language models in code generation from scientific plots. arXiv preprint arXiv:2405.07990. [find](https://scholar.google.com/scholar?q=Chengyue+Wu%2C+Yixiao+Ge%2C+Qiushan+Guo%2C+Jiahao+Wang%2C+Zhixuan+Liang%2C+Zeyu+Lu%2C+Ying+Shan%2C+and+Ping+Luo%2E+2024%2E+Plot2code%3A+A+comprehensive+benchmark+for+evaluating+multi%2Dmodal+large+language+models+in+code+g)
29. Renqiu Xia, Bo Zhang, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Min Dou, Botian Shi, Junchi Yan, et al. 2024. Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv preprint arXiv:2402.12185. — [arXiv:2402.12185](https://arxiv.org/abs/2402.12185) [find](https://scholar.google.com/scholar?q=Renqiu+Xia%2C+Bo+Zhang%2C+Hancheng+Ye%2C+Xiangchao+Yan%2C+Qi+Liu%2C+Hongbin+Zhou%2C+Zijun+Chen%2C+Min+Dou%2C+Botian+Shi%2C+Junchi+Yan%2C+et+al%2E+2024%2E+Chartx+%26+chartvlm%3A+A+versatile+benchmark+and+foundation+model+for+comp)
30. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. 2023. [Wizardlm: Empowering large language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). arXiv preprint arXiv:2304.12244.
31. Zhishen Yang, Raj Dabre, Hideki Tanaka, and Naoaki Okazaki. 2024. Scicap+: A knowledge augmented dataset to study the challenges of scientific figure captioning. Journal of Natural Language Processing, 31(3):1140–1165. [find](https://scholar.google.com/scholar?q=Zhishen+Yang%2C+Raj+Dabre%2C+Hideki+Tanaka%2C+and+Naoaki+Okazaki%2E+2024%2E+Scicap%2B%3A+A+knowledge+augmented+dataset+to+study+the+challenges+of+scientific+figure+captioning%2E+Journal+of+Natural+Language+Processing)
32. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al. 2024. [Minicpm-v: A gpt-4v level mllm on your phone](https://md.research.elamur.ai/free/en/papers/yao-2024-minicpm-v-gpt-4v/). arXiv preprint arXiv:2408.01800.
33. Yahan Yu, Duzhen Zhang, Yong Ren, Xuanle Zhao, Xiuyi Chen, and Chenhui Chu. 2025. Progressive lora for multimodal continual instruction tuning. In Findings of the Association for Computational Linguistics ACL 2025. [find](https://scholar.google.com/scholar?q=Yahan+Yu%2C+Duzhen+Zhang%2C+Yong+Ren%2C+Xuanle+Zhao%2C+Xiuyi+Chen%2C+and+Chenhui+Chu%2E+2025%2E+Progressive+lora+for+multimodal+continual+instruction+tuning%2E+In+Findings+of+the+Association+for+Computational+Linguis)
34. Tinychart: Efficient chart understanding with visual token merging and program-of-thoughts learning. arXiv preprint arXiv:2404.16635. — [arXiv:2404.16635](https://arxiv.org/abs/2404.16635) [find](https://scholar.google.com/scholar?q=Tinychart%3A+Efficient+chart+understanding+with+visual+token+merging+and+program%2Dof%2Dthoughts+learning%2E+arXiv+preprint+arXiv%3A2404%2E16635%2E+%E2%80%94+%5BarXiv%3A2404%2E16635%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2404%2E16635%29)
35. Wenqi Zhang, Zhenglin Cheng, Yuanyu He, Mengna Wang, Yongliang Shen, Zeqi Tan, Guiyang Hou, Mingqian He, Yanna Ma, Weiming Lu, et al. 2024c. Multimodal self-instruct: Synthetic abstract image and visual reasoning instruction using language model. arXiv preprint arXiv:2407.07053. [find](https://scholar.google.com/scholar?q=Wenqi+Zhang%2C+Zhenglin+Cheng%2C+Yuanyu+He%2C+Mengna+Wang%2C+Yongliang+Shen%2C+Zeqi+Tan%2C+Guiyang+Hou%2C+Mingqian+He%2C+Yanna+Ma%2C+Weiming+Lu%2C+et+al%2E+2024c%2E+Multimodal+self%2Dinstruct%3A+Synthetic+abstract+image+and+visu)
36. Zhehao Zhang, Weicheng Ma, and Soroush Vosoughi. 2024d. Is gpt-4v (ision) all you need for automating academic data visualization? exploring vision-language models’ capability in reproducing academic charts. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8271–8288. [find](https://scholar.google.com/scholar?q=Zhehao+Zhang%2C+Weicheng+Ma%2C+and+Soroush+Vosoughi%2E+2024d%2E+Is+gpt%2D4v+%28ision%29+all+you+need+for+automating+academic+data+visualization%3F+exploring+vision%2Dlanguage+models%E2%80%99+capability+in+reproducing+academic+)
37. Xuanle Zhao, Xuexin Liu, Haoyue Yang, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, and Chi Chen. 2025. Chartedit: How far are mllms from automating chart analysis? evaluating mllms’ capability via chart editing. arXiv preprint arXiv:2505.11935. [find](https://scholar.google.com/scholar?q=Xuanle+Zhao%2C+Xuexin+Liu%2C+Haoyue+Yang%2C+Xianzhen+Luo%2C+Fanhu+Zeng%2C+Jianling+Li%2C+Qi+Shi%2C+and+Chi+Chen%2E+2025%2E+Chartedit%3A+How+far+are+mllms+from+automating+chart+analysis%3F+evaluating+mllms%E2%80%99+capability+via+c)
38. Wenqing Zheng, S P Sharan, Ajay Jaiswal, Kevin Wang, Yihan Xi, Dejia Xu, and Zhangyang Wang. 2023. Outline, then details: Syntactically guided coarse-to-fine code generation. In International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Wenqing+Zheng%2C+S+P+Sharan%2C+Ajay+Jaiswal%2C+Kevin+Wang%2C+Yihan+Xi%2C+Dejia+Xu%2C+and+Zhangyang+Wang%2E+2023%2E+Outline%2C+then+details%3A+Syntactically+guided+coarse%2Dto%2Dfine+code+generation%2E+In+International+Conferen)
39. Sukmin Yun, Haokun Lin, Rusiru Thushara, Mohammad Qazim Bhat, Yongxin Wang, Zutao Jiang, Mingkai Deng, Jinhong Wang, Tianhua Tao, Junbo Li, et al. 2024. Web2code: A large-scale webpage-to-code dataset and evaluation framework for multimodal llms. arXiv preprint arXiv:2406.20098. — [arXiv:2406.20098](https://arxiv.org/abs/2406.20098) [find](https://scholar.google.com/scholar?q=Sukmin+Yun%2C+Haokun+Lin%2C+Rusiru+Thushara%2C+Mohammad+Qazim+Bhat%2C+Yongxin+Wang%2C+Zutao+Jiang%2C+Mingkai+Deng%2C+Jinhong+Wang%2C+Tianhua+Tao%2C+Junbo+Li%2C+et+al%2E+2024%2E+Web2code%3A+A+large%2Dscale+webpage%2Dto%2Dcode+dataset)
40. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023a. [Sigmoid loss for language image pre-training](https://md.research.elamur.ai/free/en/papers/zhai-2023-sigmoid-loss-language-image-pre/). 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 11941–11952.
41. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023b. [Sigmoid loss for language image pre-training](https://md.research.elamur.ai/free/en/papers/zhai-2023-sigmoid-loss-language-image-pre/). In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 11975–11986.
42. Duzhen Zhang, Yong Ren, Zhong-Zhi Li, Yahan Yu, Jiahua Dong, Chenxing Li, Zhilong Ji, and Jinfeng Bai. 2025. Enhancing multimodal continual instruction tuning with branchlora. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Duzhen+Zhang%2C+Yong+Ren%2C+Zhong%2DZhi+Li%2C+Yahan+Yu%2C+Jiahua+Dong%2C+Chenxing+Li%2C+Zhilong+Ji%2C+and+Jinfeng+Bai%2E+2025%2E+Enhancing+multimodal+continual+instruction+tuning+with+branchlora%2E+In+Proceedings+of+the+63)
43. Fengji Zhang, Linquan Wu, Huiyu Bai, Guancheng Lin, Xiao Li, Xiao Yu, Yue Wang, Bei Chen, and Jacky Keung. 2024a. Humaneval-v: Evaluating visual understanding and reasoning abilities of large multimodal models through coding tasks. arXiv preprint arXiv:2410.12381. — [arXiv:2410.12381](https://arxiv.org/abs/2410.12381) [find](https://scholar.google.com/scholar?q=Fengji+Zhang%2C+Linquan+Wu%2C+Huiyu+Bai%2C+Guancheng+Lin%2C+Xiao+Li%2C+Xiao+Yu%2C+Yue+Wang%2C+Bei+Chen%2C+and+Jacky+Keung%2E+2024a%2E+Humaneval%2Dv%3A+Evaluating+visual+understanding+and+reasoning+abilities+of+large+multimod)
44. Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, and Fei Huang. 2024b. [find](https://scholar.google.com/scholar?q=Liang+Zhang%2C+Anwen+Hu%2C+Haiyang+Xu%2C+Ming+Yan%2C+Yichen+Xu%2C+Qin+Jin%2C+Ji+Zhang%2C+and+Fei+Huang%2E+2024b%2E)

*Updated 31 October 2026*