---
title: "MM-Eureka — paper by Meng et al. (2025) — summary and ideas"
description: "Rule-based reinforcement learning in the style of DeepSeek-R1 has greatly improved text-only… 42 references, cited by 49 papers here."
authors: ["Fanqing Meng", "Lingxiao Du", "Zongkai Liu", "Zhixiang Zhou", "Quanfeng Lu", "Daocheng Fu", "Tiancheng Han", "Botian Shi", "Wenhai Wang", "Junjun He", "Kaipeng Zhang", "Ping Luo", "Yu Qiao", "Qiaosheng Zhang", "Wenqi Shao"]
year: 2025
venue: "arXiv:2503.07365"
source: "https://arxiv.org/abs/2503.07365"
doi: "10.48550/arxiv.2503.07365"
arxiv: "2503.07365"
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/meng-2025-mm-eureka-exploring-frontiers-multimodal/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/meng-2025-mm-eureka-exploring-frontiers-multimodal/)

[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/3/) / MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

# MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

**Authors:** [Fanqing Meng](https://md.research.elamur.ai/free/en/authors/fanqing-meng/), Lingxiao Du, Zongkai Liu, Zhixiang Zhou, [Quanfeng Lu](https://md.research.elamur.ai/free/en/authors/quanfeng-lu/), [Daocheng Fu](https://md.research.elamur.ai/free/en/authors/daocheng-fu/), Tiancheng Han, [Botian Shi](https://md.research.elamur.ai/free/en/authors/botian-shi/), [Wenhai Wang](https://md.research.elamur.ai/free/en/authors/wenhai-wang/), Junjun He, [Kaipeng Zhang](https://md.research.elamur.ai/free/en/authors/kaipeng-zhang/), [Ping Luo](https://md.research.elamur.ai/free/en/authors/ping-luo/), [Yu Qiao](https://md.research.elamur.ai/free/en/authors/yu-qiao/), Qiaosheng Zhang and [Wenqi Shao](https://md.research.elamur.ai/free/en/authors/wenqi-shao/) · **Year:** 2025 · **Venue:** arXiv:2503.07365 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2503.07365) · [PDF](https://arxiv.org/pdf/2503.07365) · [DOI 10.48550/arxiv.2503.07365](https://doi.org/10.48550/arxiv.2503.07365) · [arXiv 2503.07365](https://arxiv.org/abs/2503.07365) · [OpenAlex](https://openalex.org/W4416053139)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [49](https://md.research.elamur.ai/free/en/papers/meng-2025-mm-eureka-exploring-frontiers-multimodal/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Rule-based reinforcement learning in the style of DeepSeek-R1 has greatly improved text-only reasoning. Earlier attempts to bring it to vision-language models used small models and easy tasks, and their training often became unstable. The authors address this with two contributions. The first is MMK12, a multimodal mathematics dataset covering elementary through high school, with human-checked answers and worked solutions. The second is MM-Eureka, a pair of models (7B and 32B) trained with GRPO and simple rule-based rewards. Training stays stable because prompts that yield no learning signal are removed on the fly. The 32B model also gets a second, KL-regularized training stage. Although training used only math, the models also improved on physics, chemistry and biology questions. MM-Eureka-32B comes close to o1 on the multidisciplinary test and beats many larger open models. The authors argue that RL mostly makes correct answers more likely rather than teaching new knowledge. They also report that it generalizes better than SFT. All data, code and models are publicly released, which gives the open community a reproducible recipe for multimodal reasoning.

## Key points
- **MMK12**: the training split covers K12 math topics such as functions, geometry and equations. The evaluation split has 500 multiple-choice multimodal questions in each of four subjects (math, physics, chemistry, biology), checked for no overlap with training.
- **Models and method**: MM-Eureka-7B is built on Qwen2.5-VL-Instruct-7B and MM-Eureka-32B on Qwen2.5-VL-Instruct-32B. Both use GRPO plus PRIME-style online filtering, which drops prompts the model answers entirely right or entirely wrong.
- **Two-stage schedule (32B)**: the first stage runs RL on MMK12 without a KL penalty. The second stage continues on Geo3k with KL regularization to fix domain gaps and keep training stable.
- **Results**: MM-Eureka-7B scores 66.1 on MMK12 (0.2 below InternVL2.5-78B) and 73.0 on MathVista. MM-Eureka-32B reaches 72.3 on MMK12 (Qwen2.5-VL-72B: 70.3; o1: 73.9), 73.4 on WeMath and 74.8 on MathVista.
- **Release**: code, models and data are available at github.com/ModalMinds/MM-EUREKA.

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

📚 Shelves (3): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,621 works

🧭 Topics (2): [🧮 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: Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, Daocheng Fu, Tiancheng Han, Botian Shi, Wenhai Wang, Junjun He, Kaipeng Zhang, Ping Luo, Yu Qiao, Qiaosheng Zhang and Wenqi Shao. 2025. MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning. arXiv:2503.07365.

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

```bibtex
@misc{meng2025mm,
  title = {{MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning}},
  author = {Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, Daocheng Fu, Tiancheng Han, Botian Shi, Wenhai Wang, Junjun He, Kaipeng Zhang, Ping Luo, Yu Qiao, Qiaosheng Zhang and Wenqi Shao},
  year = {2025},
  doi = {10.48550/arxiv.2503.07365},
  eprint = {2503.07365},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2503.07365}
}
```

- [← previous HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://md.research.elamur.ai/free/en/papers/hu-2025-hiagent-hierarchical-working-memory-management/)
- [next → Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://md.research.elamur.ai/free/en/papers/ma-2025-pragmatics-era-large-language-models/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

42 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, and Sara Hooker. Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms. In Proceedings of the 62nd Annual Meeting of the Association for Computat… [find](https://scholar.google.com/scholar?q=Arash+Ahmadian%2C+Chris+Cremer%2C+Matthias+Galle%CC%81%2C+Marzieh+Fadaee%2C+Julia+Kreutzer%2C+Olivier+Pietquin%2C+Ahmet+U%CC%88stu%CC%88n%2C+and+Sara+Hooker%2E+Back+to+basics%3A+Revisiting+reinforce%2Dstyle+optimization+for+learning+fr)
2. Anthropic. Claude 3.7 sonnet. [https://www.anthropic.com/claude](https://www.anthropic.com/claude), 2024. Accessed: 2025-04-14. [↗](https://www.anthropic.com/claude)
3. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. [Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-vl-versatile-vision-language/), 2023. URL https://arxiv.org/abs/2308.12966. [↗](https://arxiv.org/abs/2308.12966)
4. Liang Chen, Lei Li, Haozhe Zhao, Yifan Song, and Vinci. R1-v: Reinforcing super generalization ability in vision-language models with less than $3. [https://github.com/Deep-Agent/](https://github.com/Deep-Agent/) R1-V, 2025. Accessed: 2025-02-02. [↗](https://github.com/Deep-Agent/)
5. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, et al. [Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling](https://md.research.elamur.ai/free/en/papers/chen-2024-expanding-performance-boundaries-open/). arXiv preprint arXiv:2412.05271, 2024.
6. Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, Jiarui Yuan, Huayu Chen, Kaiyan Zhang, Xingtai Lv, Shuo Wang, Yuan Yao, Xu Han, Hao Peng, Yu Cheng, Zhiyuan Liu, Maosong Sun, Bowen Zhou, and Ning Ding. Process reinforcement through… — [Process Reinforcement through Implicit Rewards](https://md.research.elamur.ai/free/en/papers/cui-2025-process-reinforcement-through-implicit-rewards/)
7. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… — [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/)
8. Linger Deng, Yuliang Liu, Bohan Li, Dongliang Luo, Liang Wu, Chengquan Zhang, Pengyuan Lyu, Ziyang Zhang, Gang Zhang, Errui Ding, et al. R-cot: Reverse chain-of-thought problem generation for geometric reasoning in large multimodal models. arXiv preprint arXiv:2410.17885, 2024. — [arXiv:2410.17885](https://arxiv.org/abs/2410.17885) [find](https://scholar.google.com/scholar?q=Linger+Deng%2C+Yuliang+Liu%2C+Bohan+Li%2C+Dongliang+Luo%2C+Liang+Wu%2C+Chengquan+Zhang%2C+Pengyuan+Lyu%2C+Ziyang+Zhang%2C+Gang+Zhang%2C+Errui+Ding%2C+et+al%2E+R%2Dcot%3A+Reverse+chain%2Dof%2Dthought+problem+generation+for+geometri)
9. Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, and Kai-Wei Chang. Openvlthinker: An early exploration to complex vision-language reasoning via iterative self-improvement, 2025. URL https://arxiv.org/abs/2503.17352. — [arXiv:2503.17352](https://arxiv.org/abs/2503.17352) [↗](https://arxiv.org/abs/2503.17352)
10. Haodong Duan, Junming Yang, Yuxuan Qiao, Xinyu Fang, Lin Chen, Yuan Liu, Xiaoyi Dong, Yuhang Zang, Pan Zhang, Jiaqi Wang, et al. Vlmevalkit: An open-source toolkit for evaluating large multi-modality models. In Proceedings of the 32nd ACM international conference on multimedia, pp. 11198–11201, 2024… [find](https://scholar.google.com/scholar?q=Haodong+Duan%2C+Junming+Yang%2C+Yuxuan+Qiao%2C+Xinyu+Fang%2C+Lin+Chen%2C+Yuan+Liu%2C+Xiaoyi+Dong%2C+Yuhang+Zang%2C+Pan+Zhang%2C+Jiaqi+Wang%2C+et+al%2E+Vlmevalkit%3A+An+open%2Dsource+toolkit+for+evaluating+large+multi%2Dmodality+)
11. Leo Gao, John Schulman, and Jacob Hilton. [Scaling laws for reward model overoptimization](https://md.research.elamur.ai/free/en/papers/gao-2022-scaling-laws-reward-model-overoptimization/), 2022. URL https://arxiv.org/abs/2210.10760. [↗](https://arxiv.org/abs/2210.10760)
12. Lujun Gui and Qingnan Ren. Training reasoning model with dynamic advantage estimation on reinforcement learning. [https://www.notion.so/Training_Reasoning_Model_](https://www.notion.so/Training_Reasoning_Model_) with_Dynamic_Advantage_Estimation_on_Reinforcement_Learning_ 1a830cc0904681fa9df3e076b6557a3e, 2025. Notion Blog. [↗](https://www.notion.so/Training_Reasoning_Model_)
13. Jarvis Guo, Tuney Zheng, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Yizhi Li, Graham Neubig, Wenhu Chen, and Xiang Yue. [Mammoth-vl: Eliciting multimodal reasoning with instruction tuning at scale](https://md.research.elamur.ai/free/en/papers/guo-2025-mammoth-vl-eliciting-multimodal-reasoning/), 2024. URL https://arxiv.org/abs/2412.05237. [↗](https://arxiv.org/abs/2412.05237)
14. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, and Maosong Sun. [Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems](https://md.research.elamur.ai/free/en/papers/he-2024-olympiadbench-challenging-benchmark-promoting-agi/), 2024. URL…
15. Jian Hu. Reinforce++: A simple and efficient approach for aligning large language models. arXiv preprint arXiv:2501.[03262, 2025](https://md.research.elamur.ai/free/en/papers/hu-2025-reinforce-stabilizing-critic-free-policy/).
16. Jian Hu, Xibin Wu, Zilin Zhu, Xianyu, Weixun Wang, Dehao Zhang, and Yu Cao. [Openrlhf: An easy-to-use, scalable and high-performance rlhf framework](https://md.research.elamur.ai/free/en/papers/hu-2024-openrlhf-easy-use-scalable/), 2024. URL https://arxiv.org/abs/2405.11143. [↗](https://arxiv.org/abs/2405.11143)
17. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276, 2024.
18. Wouter Kool, Herke van Hoof, and Max Welling. Buy 4 REINFORCE samples, get a baseline for free! In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop. [find](https://scholar.google.com/scholar?q=Wouter+Kool%2C+Herke+van+Hoof%2C+and+Max+Welling%2E+Buy+4+REINFORCE+samples%2C+get+a+baseline+for+free%21+In+Deep+Reinforcement+Learning+Meets+Structured+Prediction%2C+ICLR+2019+Workshop%2E)
19. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023.
20. Pan Lu, Ran Gong, Shibiao Jiang, Liang Qiu, Siyuan Huang, Xiaodan Liang, and Song-Chun Zhu. [Inter-gps: Interpretable geometry problem solving with formal language and symbolic reasoning](https://md.research.elamur.ai/free/en/papers/lu-2021-inter-gps-interpretable-geometry-problem/). arXiv preprint arXiv:2105.04165, 2021.
21. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. [Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts](https://md.research.elamur.ai/free/en/papers/lu-2023-mathvista-evaluating-mathematical-reasoning-foundation/), 2024. URL https://arxiv.org/abs/2310. 02255. [↗](https://arxiv.org/abs/2310)
22. OpenAI. Introducing openai o1. [https://openai.com/o1/](https://openai.com/o1/), 2024. Accessed: 2024-10-02. [↗](https://openai.com/o1/)
23. 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. Training la… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
24. Shuai Peng, Di Fu, Liangcai Gao, Xiuqin Zhong, Hongguang Fu, and Zhi Tang. Multimath: Bridging visual and mathematical reasoning for large language models. arXiv preprint arXiv:2409.00147, 2024. — [arXiv:2409.00147](https://arxiv.org/abs/2409.00147) [find](https://scholar.google.com/scholar?q=Shuai+Peng%2C+Di+Fu%2C+Liangcai+Gao%2C+Xiuqin+Zhong%2C+Hongguang+Fu%2C+and+Zhi+Tang%2E+Multimath%3A+Bridging+visual+and+mathematical+reasoning+for+large+language+models%2E+arXiv+preprint+arXiv%3A2409%2E00147%2C+2024%2E+%E2%80%94+%5Bar)
25. YingZhe Peng, Gongrui Zhang, Xin Geng, and Xu Yang. Lmm-r1. [https://github.com/](https://github.com/) TideDra/lmm-r1, 2025. Accessed: 2025-02-13. [↗](https://github.com/)
26. Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma Gongque, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, and Honggang Zhang. We-math: Does your large multimodal model achieve human-like mathemati… — [We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?](https://md.research.elamur.ai/free/en/papers/qiao-2024-math-large-multimodal-model-achieve/)
27. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2C+2019%2E)
28. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in Neural Information Processing Systems, 36:53728–53741, 2023.
29. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms, 2017a. URL https://arxiv.org/abs/1707.06347. [↗](https://arxiv.org/abs/1707.06347)
30. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017b. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2C+2017b%2E)
31. Richard S Sutton, Andrew G Barto, et al. Reinforcement learning: An introduction, volume 1. MIT press Cambridge, 1998. [find](https://scholar.google.com/scholar?q=Richard+S+Sutton%2C+Andrew+G+Barto%2C+et+al%2E+Reinforcement+learning%3A+An+introduction%2C+volume+1%2E+MIT+press+Cambridge%2C+1998%2E)
32. Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Minglan Lin, Pengwei Wang, Zhongyuan Wang, and Shanghang Zhang. Reason-rft: Reinforcement fine-tuning for visual reasoning, 2025. URL https://arxiv.org/abs/2503.20752. — [arXiv:2503.20752](https://arxiv.org/abs/2503.20752) [↗](https://arxiv.org/abs/2503.20752)
33. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. [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, 2023.
34. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, Chuning Tang, Congcong Wang, Dehao Zhang, Enming Yuan, Enzhe Lu, Fengxiang Tang, Flood Sung, Guangda Wei, Guokun Lai, Haiqing Guo, Han Zhu, Hao Ding, Hao Hu, Hao Yang, Hao Z… — [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/)
35. Kimi Team, Angang Du, Bohong Yin, Bowei Xing, Bowen Qu, Bowen Wang, Cheng Chen, Chenlin Zhang, Chenzhuang Du, Chu Wei, Congcong Wang, Dehao Zhang, Dikang Du, Dongliang Wang, Enming Yuan, Enzhe Lu, Fang Li, Flood Sung, Guangda Wei, Guokun Lai, Han Zhu, Hao Ding, Hao Hu, Hao Yang, Hao Zhang, Haoning W… — [Kimi-VL Technical Report](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-vl-technical-report/)
36. Qwen Team. Qvq: To see the world with wisdom, December 2024. URL [https://qwenlm.github.io/blog/qvq-72b-preview/](https://qwenlm.github.io/blog/qvq-72b-preview/). [↗](https://qwenlm.github.io/blog/qvq-72b-preview/)
37. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Mingjie Zhan, and Hongsheng Li. [Measuring multimodal mathematical reasoning with math-vision dataset](https://md.research.elamur.ai/free/en/papers/wang-2024-measuring-multimodal-mathematical-reasoning-math/), 2024a. URL [https://arxiv.org/](https://arxiv.org/) abs/2402.14804. [↗](https://arxiv.org/)
38. Weiyun Wang, Zhe Chen, Wenhai Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Jinguo Zhu, Xizhou Zhu, Lewei Lu, Yu Qiao, and Jifeng Dai. [Enhancing the reasoning ability of multimodal large language models via mixed preference optimization](https://md.research.elamur.ai/free/en/papers/wang-2024-enhancing-reasoning-ability-multimodal-large/), 2024b. URL https://arxiv.org/abs/2411.10442. [↗](https://arxiv.org/abs/2411.10442)
39. Yi Yang, Xiaoxuan He, Hongkun Pan, Xiyan Jiang, Yan Deng, Xingtao Yang, Haoyu Lu, Dacheng Yin, Fengyun Rao, Minfeng Zhu, Bo Zhang, and Wei Chen. [R1-onevision: Advancing generalized multimodal reasoning through cross-modal formalization](https://md.research.elamur.ai/free/en/papers/yang-2025-r1-onevision-advancing-generalized-multimodal/). arXiv preprint arXiv:2503.10615, 2025.
40. Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Peng Gao, and Hongsheng Li. [Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?](https://md.research.elamur.ai/free/en/papers/zhang-2024-mathverse-multi-modal-llm-truly/), 2024a. URL https://arxiv.org/abs/ 2403.14624. [↗](https://arxiv.org/abs/)
41. Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Ziyu Guo, Shicheng Li, Yichi Zhang, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, et al. Mavis: Mathematical visual instruction tuning with an automatic data engine. arXiv preprint arXiv:2407.08739, 2024b. — [arXiv:2407.08739](https://arxiv.org/abs/2407.08739) [find](https://scholar.google.com/scholar?q=Renrui+Zhang%2C+Xinyu+Wei%2C+Dongzhi+Jiang%2C+Ziyu+Guo%2C+Shicheng+Li%2C+Yichi+Zhang%2C+Chengzhuo+Tong%2C+Jiaming+Liu%2C+Aojun+Zhou%2C+Bin+Wei%2C+et+al%2E+Mavis%3A+Mathematical+visual+instruction+tuning+with+an+automatic+dat)
42. Yuze Zhao, Jintao Huang, Jinghan Hu, Xingjun Wang, Yunlin Mao, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, Wenmeng Zhou, and Yingda Chen. Swift:a scalable lightweight infrastructure for fine-tuning, 2024. URL https://arxiv.org/abs/2408.05517. — [arXiv:2408.05517](https://arxiv.org/abs/2408.05517) [↗](https://arxiv.org/abs/2408.05517)

*Updated 3 November 2026*