---
title: "ChartGemma — paper by Masry et al. (2024)"
description: "Most chart-understanding models learn from instruction data built from a chart's underlying data table. 39 references, cited by 32 papers here."
authors: ["Ahmed Masry", "Megh Thakkar", "Aayush Bajaj", "Aaryaman Kartha", "Enamul Hoque", "Shafiq Joty"]
year: 2024
venue: "arXiv:2407.04172"
source: "https://arxiv.org/abs/2407.04172"
doi: "10.48550/arxiv.2407.04172"
arxiv: "2407.04172"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/masry-2024-chartgemma-visual-instruction-tuning-chart/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/masry-2024-chartgemma-visual-instruction-tuning-chart/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/10/) / ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild

# ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild

**Authors:** [Ahmed Masry](https://md.research.elamur.ai/free/en/authors/ahmed-masry/), [Megh Thakkar](https://md.research.elamur.ai/free/en/authors/megh-thakkar/), Aayush Bajaj, Aaryaman Kartha, [Enamul Hoque](https://md.research.elamur.ai/free/en/authors/enamul-hoque/) and [Shafiq Joty](https://md.research.elamur.ai/free/en/authors/shafiq-joty/) · **Year:** 2024 · **Venue:** arXiv:2407.04172 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2407.04172) · [PDF](https://arxiv.org/pdf/2407.04172) · [DOI 10.48550/arxiv.2407.04172](https://doi.org/10.48550/arxiv.2407.04172) · [arXiv 2407.04172](https://arxiv.org/abs/2407.04172) · [OpenAlex](https://openalex.org/W4400434413)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [32](https://md.research.elamur.ai/free/en/papers/masry-2024-chartgemma-visual-instruction-tuning-chart/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most chart-understanding models learn from instruction data built from a chart's underlying data table. That approach discards visual cues such as trends, annotations and layout. These models also often use vision-language backbones whose image and text parts are only loosely aligned. ChartGemma addresses both problems. The authors collected 122,857 chart images from three kinds of sources: synthetic (e.g., PlotQA), curated (Statista) and stylistically varied web charts (WebCharts). Gemini Flash 1.5 then generated instruction–response pairs from the images alone. The tasks cover chain-of-thought reasoning, summarization, fact checking, chart-to-markdown conversion and open-ended requests. The authors fine-tuned PaliGemma, a strongly aligned and relatively compact VLM, on this data. The resulting model achieves state-of-the-art results on five benchmarks for chart summarization, question answering and fact-checking. Human and GPT4-based assessments indicate that its summaries of real-world charts are more faithful and informative than those of rival systems. The work shows that image-grounded instructions combined with a well-aligned backbone can outperform larger chart models. Code, checkpoints, data and demos are publicly released.

## Key points
- The backbone is PaliGemma. The resulting model is notably smaller than competing chart-understanding models.
- The instruction corpus has 122,857 chart images, and Gemini Flash 1.5 generated all instructions without using metadata or data tables. Existing chart fact-checking training sets were added to this data.
- ChartGemma sets state-of-the-art results on 5 benchmarks covering summarization, QA and fact-checking.
- Informativeness and Factual Correctness were judged with GPT4, which raises reproducibility concerns. The vision encoder input is limited to 448x448.
- Resources are available at github.com/vis-nlp/ChartGemma. Images are released where licenses permit, and URLs are provided otherwise.

*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

- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 193 works · 27,739 citations
- [Mila - Quebec Artificial Intelligence Institute](https://md.research.elamur.ai/free/en/labs/mila-quebec-artificial-intelligence-institute/) — Research institute, Montreal, Canada · 73 works · 14,704 citations
- [York University](https://md.research.elamur.ai/free/en/universities/york-university/) — University, Toronto, Canada · 18 works · 3,378 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,621 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,948 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 827 works

## Cite

Cite as: Ahmed Masry, Megh Thakkar, Aayush Bajaj, Aaryaman Kartha, Enamul Hoque and Shafiq Joty. 2024. ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild. arXiv:2407.04172.

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

```bibtex
@misc{masry2024chartgemma,
  title = {{ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild}},
  author = {Ahmed Masry, Megh Thakkar, Aayush Bajaj, Aaryaman Kartha, Enamul Hoque and Shafiq Joty},
  year = {2024},
  doi = {10.48550/arxiv.2407.04172},
  eprint = {2407.04172},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2407.04172}
}
```

- [← previous AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://md.research.elamur.ai/free/en/papers/kramar-2024-atp-efficient-scalable-method-localizing/)
- [next → Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://md.research.elamur.ai/free/en/papers/ding-2024-data-augmentation-using-large-language/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/10/)

## References

39 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mubashara Akhtar, Oana Cocarascu, and Elena Simperl. 2023a. Reading and reasoning over chart images for evidence-based automated fact-checking. arXiv preprint arXiv:2301.11843. [find](https://scholar.google.com/scholar?q=Mubashara+Akhtar%2C+Oana+Cocarascu%2C+and+Elena+Simperl%2E+2023a%2E+Reading+and+reasoning+over+chart+images+for+evidence%2Dbased+automated+fact%2Dchecking%2E+arXiv+preprint+arXiv%3A2301%2E11843%2E)
2. Mubashara Akhtar, Oana Cocarascu, and Elena Simperl. 2023b. Reading and reasoning over chart images for evidence-based automated fact-checking. In Findings of the Association for Computational Linguistics: EACL 2023, pages 399–414, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mubashara+Akhtar%2C+Oana+Cocarascu%2C+and+Elena+Simperl%2E+2023b%2E+Reading+and+reasoning+over+chart+images+for+evidence%2Dbased+automated+fact%2Dchecking%2E+In+Findings+of+the+Association+for+Computational+Linguis)
3. Mubashara Akhtar, Nikesh Subedi, Vivek Gupta, Sahar Tahmasebi, Oana Cocarascu, and Elena Simperl. 2023c. Chartcheck: An evidence-based fact-checking dataset over real-world chart images. arXiv preprint arXiv:2311.07453. — [arXiv:2311.07453](https://arxiv.org/abs/2311.07453) [find](https://scholar.google.com/scholar?q=Mubashara+Akhtar%2C+Nikesh+Subedi%2C+Vivek+Gupta%2C+Sahar+Tahmasebi%2C+Oana+Cocarascu%2C+and+Elena+Simperl%2E+2023c%2E+Chartcheck%3A+An+evidence%2Dbased+fact%2Dchecking+dataset+over+real%2Dworld+chart+images%2E+arXiv+preprin)
4. Alpaca. 2023. Alpaca. [https://crfm.stanford.edu/2023/03/13/alpaca.html](https://crfm.stanford.edu/2023/03/13/alpaca.html) . [↗](https://crfm.stanford.edu/2023/03/13/alpaca.html)
5. Lucas Beyer, Andreas Steiner, André Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, Thomas Unterthiner, Daniel Keysers, Skanda Koppula, Fangyu Liu, Adam Grycner, Alexey Gritsenko, Neil Houlsby, Manoj Kumar, Ke… — [PaliGemma: A versatile 3B VLM for transfer](https://md.research.elamur.ai/free/en/papers/beyer-2024-paligemma-versatile-3b-vlm-transfer/)
6. Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. [Re-evaluating the role of Bleu in machine translation research](https://md.research.elamur.ai/free/en/papers/burch-2006-re-evaluating-role-bleu-machine/). In 11th Conference of the European Chapter of the Association for Computational Linguistics, pages 249–256, Trento, Italy. Association for Computational Linguistics.
7. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. [find](https://scholar.google.com/scholar?q=Wei%2DLin+Chiang%2C+Zhuohan+Li%2C+Zi+Lin%2C+Ying+Sheng%2C+Zhanghao+Wu%2C+Hao+Zhang%2C+Lianmin+Zheng%2C+Siyuan+Zhuang%2C+Yonghao+Zhuang%2C+Joseph+E%2E+Gonzalez%2C+Ion+Stoica%2C+and+Eric+P%2E+Xing%2E+2023%2E+Vicuna%3A+An+open%2Dsource+cha)
8. J. Choi, Sanghun Jung, Deok Gun Park, J. Choo, and N. Elmqvist. 2019. Visualizing for the non-visual: Enabling the visually impaired to use visualization. Computer Graphics Forum, 38. [find](https://scholar.google.com/scholar?q=J%2E+Choi%2C+Sanghun+Jung%2C+Deok+Gun+Park%2C+J%2E+Choo%2C+and+N%2E+Elmqvist%2E+2019%2E+Visualizing+for+the+non%2Dvisual%3A+Enabling+the+visually+impaired+to+use+visualization%2E+Computer+Graphics+Forum%2C+38%2E)
9. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. [Instructblip: Towards general-purpose vision-language models with instruction tuning](https://md.research.elamur.ai/free/en/papers/dai-2023-instructblip-towards-general-purpose-vision/).
10. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2022. Pal: Program-aided language models. arXiv preprint arXiv:2211.10435. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+Uri+Alon%2C+Pengfei+Liu%2C+Yiming+Yang%2C+Jamie+Callan%2C+and+Graham+Neubig%2E+2022%2E+Pal%3A+Program%2Daided+language+models%2E+arXiv+preprint+arXiv%3A2211%2E10435%2E)
11. Yucheng Han, Chi Zhang, Xin Chen, Xu Yang, Zhibin Wang, Gang Yu, Bin Fu, and Hanwang Zhang. 2023. [Chartllama: A multimodal llm for chart understanding and generation](https://md.research.elamur.ai/free/en/papers/han-2023-chartllama-multimodal-llm-chart-understanding/). arXiv preprint arXiv:2311.16483.
12. Enamul Hoque, Parsa Kavehzadeh, and Ahmed Masry. 2022. Chart question answering: State of the art and future directions. Journal of Computer Graphics Forum (Proc. EuroVis), pages 555–572. [find](https://scholar.google.com/scholar?q=Enamul+Hoque%2C+Parsa+Kavehzadeh%2C+and+Ahmed+Masry%2E+2022%2E+Chart+question+answering%3A+State+of+the+art+and+future+directions%2E+Journal+of+Computer+Graphics+Forum+%28Proc%2E+EuroVis%29%2C+pages+555%E2%80%93572%2E)
13. Shankar Kantharaj, Xuan Long Do, Rixie Tiffany Ko Leong, Jia Qing Tan, Enamul Hoque, and Shafiq Joty. 2022. Opencqa: Open-ended question answering with charts. In Proceedings of EMNLP (to appear). [find](https://scholar.google.com/scholar?q=Shankar+Kantharaj%2C+Xuan+Long+Do%2C+Rixie+Tiffany+Ko+Leong%2C+Jia+Qing+Tan%2C+Enamul+Hoque%2C+and+Shafiq+Joty%2E+2022%2E+Opencqa%3A+Open%2Dended+question+answering+with+charts%2E+In+Proceedings+of+EMNLP+%28to+appear%29%2E)
14. Kenton Lee, Mandar Joshi, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, and Kristina Toutanova. 2022. [Pix2struct: Screenshot parsing as pretraining for visual language understanding](https://md.research.elamur.ai/free/en/papers/lee-2022-pix2struct-screenshot-parsing-pretraining-visual/). arXiv preprint arXiv:2210.03347.
15. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. [Llava-med: Training a large language-and-vision assistant for biomedicine in one day](https://md.research.elamur.ai/free/en/papers/li-2023-llava-med-training-large-language/). arXiv preprint arXiv:2306.00890.
16. Fangyu Liu, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Yasemin Altun, Nigel Collier, and Julian Martin Eisenschlos. 2022. Matcha: Enhancing visual language pretraining with math reasoning and chart derendering. arXiv preprint arXiv:2212.09662. [find](https://scholar.google.com/scholar?q=Fangyu+Liu%2C+Francesco+Piccinno%2C+Syrine+Krichene%2C+Chenxi+Pang%2C+Kenton+Lee%2C+Mandar+Joshi%2C+Yasemin+Altun%2C+Nigel+Collier%2C+and+Julian+Martin+Eisenschlos%2E+2022%2E+Matcha%3A+Enhancing+visual+language+pretraining)
17. 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.
18. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). arXiv preprint arXiv:2304.08485.
19. Ahmed Masry and Enamul Hoque. 2021. Integrating image data extraction and table parsing methods for chart question answering. Chart Question Answering Workshop, in conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR), pages 1–5. [find](https://scholar.google.com/scholar?q=Ahmed+Masry+and+Enamul+Hoque%2E+2021%2E+Integrating+image+data+extraction+and+table+parsing+methods+for+chart+question+answering%2E+Chart+Question+Answering+Workshop%2C+in+conjunction+with+the+Conference+on+C)
20. 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/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (to appear). Association for Compu…
21. Ahmed Masry, Do Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022a. [ChartQA: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). In Findings of the Association for Computational Linguistics: ACL 2022, pages 2263– 2279, Dublin, Ireland. Association for Computation…
22. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022b. [Chartqa: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). arXiv preprint arXiv:2203.10244.
23. Ahmed Masry, Mehrad Shahmohammadi, Md Rizwan Parvez, Enamul Hoque, and Shafiq Joty. 2024. Chartinstruct: Instruction tuning for chart comprehension and reasoning. [find](https://scholar.google.com/scholar?q=Ahmed+Masry%2C+Mehrad+Shahmohammadi%2C+Md+Rizwan+Parvez%2C+Enamul+Hoque%2C+and+Shafiq+Joty%2E+2024%2E+Chartinstruct%3A+Instruction+tuning+for+chart+comprehension+and+reasoning%2E)
24. 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+)
25. 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 (WACV). [find](https://scholar.google.com/scholar?q=Nitesh+Methani%2C+Pritha+Ganguly%2C+Mitesh+M%2E+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)
26. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022. Cross-task generalization via natural language crowdsourcing instructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3470–3487, Dublin, Irelan… [find](https://scholar.google.com/scholar?q=Swaroop+Mishra%2C+Daniel+Khashabi%2C+Chitta+Baral%2C+and+Hannaneh+Hajishirzi%2E+2022%2E+Cross%2Dtask+generalization+via+natural+language+crowdsourcing+instructions%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+th)
27. OpenAI. 2023. [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
28. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
29. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational…
30. Matt Post. 2018. [A call for clarity in reporting BLEU scores](https://md.research.elamur.ai/free/en/papers/post-2018-call-clarity-reporting-bleu-scores/). In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Brussels, Belgium. Association for Computational Linguistics.
31. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/).
32. Kantharaj Shankar, Leong Rixie Tiffany Ko, Lin Xiang, Masry Ahmed, Thakkar Megh, Hoque Enamul, and Joty Shafiq. 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/). In In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2022.
33. Aaron Smith, Christian Hardmeier, and Joerg Tiedemann. 2016. Climbing mont BLEU: The strange world of reachable high-BLEU translations. In Proceedings of the 19th Annual Conference of the European Association for Machine Translation, pages 269–281. [find](https://scholar.google.com/scholar?q=Aaron+Smith%2C+Christian+Hardmeier%2C+and+Joerg+Tiedemann%2E+2016%2E+Climbing+mont+BLEU%3A+The+strange+world+of+reachable+high%2DBLEU+translations%2E+In+Proceedings+of+the+19th+Annual+Conference+of+the+European+Ass)
34. Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, and Jiahui Yu 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/).
35. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Léonard Hussenot, Pier Giuseppe Sessa, Aakanksha Chowdhery, Adam Roberts, Aditya Barua, Alex Botev, Alex Castro-Ros, Ambrose Sl… [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Thomas+Mesnard%2C+Cassidy+Hardin%2C+Robert+Dadashi%2C+Surya+Bhupatiraju%2C+Shreya+Pathak%2C+Laurent+Sifre%2C+Morgane+Rivi%C3%A8re%2C+Mihir+Sanjay+Kale%2C+Juliette+Love%2C+Pouya+Tafti%2C+L%C3%A9onard+Hussenot%2C+Pier+Gius)
36. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in neural information processing systems, pages 5998–6008.
37. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023. [Sigmoid loss for language image pre-training](https://md.research.elamur.ai/free/en/papers/zhai-2023-sigmoid-loss-language-image-pre/).
38. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. [Judging LLM-as-a-judge with MT-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). In Thirty-seventh Conference on Neural Information Processing…
39. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. [Minigpt-4: Enhancing vision-language understanding with advanced large language models](https://md.research.elamur.ai/free/en/papers/zhu-2023-minigpt-4-enhancing-vision-language/). arXiv preprint arXiv:2304.10592.

*Updated 3 November 2026*