Elamur Research⌕
☰
home / papers / 2025 / MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification

Paper · 2025 · Linzhuang Sun, Hao Liang, Jingxuan Wei et al.

Summary

The paper targets two gaps in multimodal math reasoning. There is no strong verifier for checking answers from multimodal LLMs, and there is little long chain-of-thought (CoT) training data with images. The authors build two 7B models. MM-Verifier is an outcome reward model that judges whether a solution to an image-based question is correct. It is trained in two stages. First, a simulation-based tree search produces long reasoning paths, and GPT-4o writes verifications of them. Then the Stage-1 verifier generates more verification data, which is filtered by rejection sampling. MM-Reasoner uses a cheaper route to long multimodal CoT data. Textual descriptions of geometric figures from MAVIS go to the text-only reasoning model Qwen QwQ, and its answers are paired with the matching images. With 12 sampled rollouts from MM-Reasoner reranked by MM-Verifier, the system scores 65.3 on MathVista, above GPT-4o (63.8) and the human baseline (60.3). The work shows that small multimodal models can benefit from test-time scaling with a dedicated verifier.

Key points

  • Verifier training questions come from Geometry3K (20,226), Super-CLEVR (14,446), TabMWP (13,418), FigureQA (10,800) and GEOS (882). MM-Reasoner data is built from MAVIS-Geo.
  • According to the authors, on MathCheck's Outcome-Judging benchmark the 7B MM-Verifier achieves better results than GPT-4o, Gemini and Claude. It also outperforms Qwen2-VL-72B on all MathVista and MathVerse metrics.
  • The combined system scores 65.3 overall on MathVista and 25.7 on MathVerse. The strongest listed open baselines are Math-LLaVA-13B (22.9 on MathVerse) and Qwen2-VL-7B (52.5 on MathVista).
  • Performance of MM-Reasoner keeps rising as the synthetic training set grows, although the reasoner alone is not state of the art.
  • Limitations: the method was not scaled to Qwen2-VL-72B, and scaling tests used fewer than 100K samples. Code is available at github.com/Aurora-slz/MM-Verify.

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

🎓Peking UniversityBeijing · China244 works · 39,359 citations🏛️Chinese Academy of SciencesBeijing · China194 works · 23,906 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🏢BaichuanBeijing · China7 works · 218 citations🏢Shenyang Institute of Computing TechnologyShenyang · China2 works · 19 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,426 worksVision & language · 657 works

Cite

Cite as Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Tianpeng Li, Fan Yang, Zenan Zhou and Wentao Zhang. 2025. MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification. 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. DOI 10.18653/v1/2025.acl-long.689

@inproceedings{sun2025mm,
  title = {{MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification}},
  author = {Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Tianpeng Li, Fan Yang, Zenan Zhou and Wentao Zhang},
  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.689},
  url = {https://doi.org/10.18653/v1/2025.acl-long.689}
}

References

65 references, 33 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023a. Qwen technical report. arXiv preprint arXiv:2309.16609.
  2. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023b. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond.
  3. Tianyi Bai, Hao Liang, Binwang Wan, Ling Yang, Bozhou Li, Yifan Wang, Bin Cui, Conghui He, Binhang Yuan, and Wentao Zhang. 2024. A survey of multimodal large language model from a data-centric perspective. arXiv preprint arXiv:2405.16640. — [arXiv:2405.16640](https://arxiv.org/abs/2405.16640) find
  4. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, and Dahua Lin. 2023. Sharegpt4v: Improving large multi-modal models with better captions. CoRR, abs/2311.12793.
  5. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025. Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. arXiv preprint arXiv:2503.09567.
  6. Qiguang Chen, Libo Qin, Jin Zhang, Zhi Chen, Xiao Xu, and Wanxiang Che. 2024a. M 3 cot: A novel benchmark for multi-domain multi-step multi-modal chain-of-thought. arXiv preprint arXiv:2405.16473.
  7. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024b. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern…
  8. Zihui Cheng, Qiguang Chen, Jin Zhang, Hao Fei, Xiaocheng Feng, Wanxiang Che, Min Li, and Libo Qin. 2025. Comt: A novel benchmark for chain of multimodal thought on large vision-language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23678–23686. find
  9. Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, et al. 2025. Process reinforcement through implicit rewards. arXiv preprint arXiv:2502.01456.
  10. Yifan Du, Zikang Liu, Yifan Li, Wayne Xin Zhao, Yuqi Huo, Bingning Wang, Weipeng Chen, Zheng Liu, Zhongyuan Wang, and Ji-Rong Wen. 2025. Virgo: A preliminary exploration on reproducing o1-like mllm. arXiv preprint arXiv:2501.01904. — [arXiv:2501.01904](https://arxiv.org/abs/2501.01904) find
  11. Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Junyang Lin, Chang Zhou, Wen Xiao, et al. 2024. Llm critics help catch bugs in mathematics: Towards a better mathematical verifier with natural language feedback. CoRR. find
  12. Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing Hong, Jianhua Han, Hang Xu, Zhenguo Li, et al. 2023. G-llava: Solving geometric problem with multi-modal large language model. arXiv preprint arXiv:2312.11370. find
  13. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, et al. 2024. A survey on llm-as-a-judge. arXiv preprint arXiv:2411.15594. find
  14. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  15. Litian Huang, Xinguo Yu, Feng Xiong, Bin He, Sheng-bing Tang, and Jiawen Fu. 2024. Hologram reasoning for solving algebra problems with geometry diagrams. arXiv preprint arXiv:2408.10592. — [arXiv:2408.10592](https://arxiv.org/abs/2408.10592) find
  16. Yiren Jian, Chongyang Gao, and Soroush Vosoughi. 2023. Bootstrapping vision-language learning with decoupled language pre-training. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 1… find
  17. Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. 2023a. Otter: A multi-modal model with in-context instruction tuning. CoRR, abs/2305.03726.
  18. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326.
  19. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, pages 19730–19742. PMLR.
  20. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023c. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, pages 19730–19742. PMLR.
  21. Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022a. BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162, pages 12888–…
  22. Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, Kai-Wei Chang, and Jianfeng Gao. 2022b. Grounded language-image pre-training. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New… find
  23. Zhihao Li, Yao Du, Yang Liu, Yan Zhang, Yufang Liu, Mengdi Zhang, and Xunliang Cai. 2024b. Eagle: Elevating geometric reasoning through llm-empowered visual instruction tuning. arXiv preprint arXiv:2408.11397. — [arXiv:2408.11397](https://arxiv.org/abs/2408.11397) find
  24. Zhenwen Liang, Tianyu Yang, Jipeng Zhang, and Xiangliang Zhang. 2023. Unimath: A foundational and multimodal mathematical reasoner. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7126–7133. find
  25. Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, et al. 2023. Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575. — [arXiv:2311.07575](https://arxiv.org/abs/2311.07575) find
  26. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744.
  27. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual instruction tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023.
  28. Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, and Lei Zhang. 2023c. Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. CoRR, abs/2303.05499.
  29. Wei Liu, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng, and Junxian He. 2024. Diving into self-evolving training for multimodal reasoning. arXiv preprint arXiv:2412.17451. — [arXiv:2412.17451](https://arxiv.org/abs/2412.17451) find
  30. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Yaofeng Sun, et al. 2024. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525.
  31. Junyu Lu, Ruyi Gan, Dixiang Zhang, Xiaojun Wu, Ziwei Wu, Renliang Sun, Jiaxing Zhang, Pingjian Zhang, and Yan Song. 2023a. Lyrics: Boosting fine-grained language-vision alignment and comprehension via semantic-aware visual objects. CoRR, abs/2312.05278. — [arXiv:2312.05278](https://arxiv.org/abs/2312.05278) find
  32. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2023b. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255.
  33. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35:2507–2521. find
  34. Ruilin Luo, Zhuofan Zheng, Yifan Wang, Yiyao Yu, Xinzhe Ni, Zicheng Lin, Jin Zeng, and Yujiu Yang. 2025. Ursa: Understanding and verifying chain-of-thought reasoning in multimodal mathematics. arXiv preprint arXiv:2501.04686. — [arXiv:2501.04686](https://arxiv.org/abs/2501.04686) find
  35. Kazem Meidani, Parshin Shojaee, Chandan K Reddy, and Amir Barati Farimani. 2023. Snip: Bridging mathematical symbolic and numeric realms with unified pre-training. arXiv preprint arXiv:2310.02227. find
  36. Yingqian Min, Zhipeng Chen, Jinhao Jiang, Jie Chen, Jia Deng, Yiwen Hu, Yiru Tang, Jiapeng Wang, Xiaoxue Cheng, Huatong Song, et al. 2024. Imitate, explore, and self-improve: A reproduction report on slow-thinking reasoning systems. arXiv preprint arXiv:2412.09413. find
  37. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393.
  38. Skywork o1 Team. 2024. Skywork-o1 open series. https://huggingface.co/Skywork. ↗
  39. R OpenAI. 2023b. Gpt-4 technical report. arxiv 2303.08774. View in Article, 2(5).
  40. 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. In International conference on machine learning, pages 8748–8763. PM…
  41. Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, and Hongsheng Li. 2024. Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. Advances in Neural Information Processing Systems, 37:8612–8642. find
  42. Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, and Roy Ka-Wei Lee. 2024. Math-llava: Bootstrapping mathematical reasoning for multimodal large language models. arXiv preprint arXiv:2406.17294.
  43. Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Conghui He, Zenan Zhou, and Wentao Zhang. 2024. Beats: Optimizing llm mathematical capabilities with backverify and adaptive disambiguate based efficient tree search. arXiv preprint arXiv:2409.17972. — [arXiv:2409.17972](https://arxiv.org/abs/2409.17972) find
  44. Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. find
  45. Omkar Thawakar, Dinura Dissanayake, Ketan More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Yuhao Li, Mohammed Zumri, Jean Lahoud, Rao Muhammad Anwer, et al. 2025. Llamav-o1: Rethinking step-by-step visual reasoning in llms. arXiv preprint arXiv:2501.06186. find
  46. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  47. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024a. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  48. Weizhi Wang, Khalil Mrini, Linjie Yang, Sateesh Kumar, Yu Tian, Xifeng Yan, and Heng Wang. 2024b. Finetuned multimodal language models are high-quality image-text data filters. CoRR, abs/2403.02677. — [arXiv:2403.02677](https://arxiv.org/abs/2403.02677) find
  49. Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, and Jun Zhao. 2022. Large language models are better reasoners with self-verification. arXiv preprint arXiv:2212.09561.
  50. Jiayang Wu, Wensheng Gan, Zefeng Chen, Shicheng Wan, and Philip S Yu. 2023. Multimodal large language models: A survey. arXiv preprint arXiv:2311.13165. — [arXiv:2311.13165](https://arxiv.org/abs/2311.13165)
  51. Wei Xiong, Hanning Zhang, Nan Jiang, and Tong Zhang. 2024. An implementation of generative prm. https://github.com/RLHFlow/RLHF-Reward-Modeling. ↗
  52. Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Anwen Hu, Haowei Liu, Qi Qian, Ji Zhang, and Fei Huang. 2024. mplug-owl2: Revolutionizing multimodal large language model with modality collaboration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13040–13051. find
  53. Yixin Ye, Zhen Huang, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu. 2025. Limo: Less is more for reasoning. arXiv preprint arXiv:2502.03387.
  54. Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li, and Wanli Ouyang. 2024a. Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b. arXiv preprint arXiv:2406.07394. find
  55. Di Zhang, Jingdi Lei, Junxian Li, Xunzhi Wang, Yujie Liu, Zonglin Yang, Jiatong Li, Weida Wang, Suorong Yang, Jianbo Wu, et al. 2024b. Critic-v: Vlm critics help catch vlm errors in multimodal reasoning. arXiv preprint arXiv:2411.18203. — [arXiv:2411.18203](https://arxiv.org/abs/2411.18203) find
  56. Haotian Zhang, Pengchuan Zhang, Xiaowei Hu, Yen-Chun Chen, Liunian Harold Li, Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, and Jianfeng Gao. 2022. Glipv2: Unifying localization and vision-language understanding. In Advances in Neural Information Processing Systems 35: Annual Conference on Neur… find
  57. Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2024c. Generative verifiers: Reward modeling as next-token prediction. arXiv preprint arXiv:2408.15240.
  58. Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Peng Gao, et al. 2024d. Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? arXiv preprint arXiv:2403.14624.
  59. Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Yichi Zhang, Ziyu Guo, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, et al. 2024e. Mavis: Mathematical visual instruction tuning. arXiv preprint arXiv:2407.08739. — [arXiv:2407.08739](https://arxiv.org/abs/2407.08739) find
  60. Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025. The lessons of developing process reward models in mathematical reasoning. arXiv preprint arXiv:2501.07301.
  61. Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923.
  62. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223.
  63. Zihao Zhou, Shudong Liu, Maizhen Ning, Wei Liu, Jindong Wang, Derek F Wong, Xiaowei Huang, Qiufeng Wang, and Kaizhu Huang. 2024. Is your model really a good math reasoner? evaluating mathematical reasoning with checklist. arXiv preprint arXiv:2407.08733. — [arXiv:2407.08733](https://arxiv.org/abs/2407.08733) find
  64. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592.
  65. Wenwen Zhuang, Xin Huang, Xiantao Zhang, and Jin Zeng. 2024. Math-puma: Progressive upward multimodal alignment to enhance mathematical reasoning. arXiv preprint arXiv:2408.08640. — [arXiv:2408.08640](https://arxiv.org/abs/2408.08640) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sun-2025-mm-verify-enhancing-multimodal-reasoning/