Elamur Research⌕
☰
home / papers / 2026 / MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper · 2026 · Junbo Niu, Zheng Liu, Zhuangcheng Gu et al.

Summary

Turning document images into structured text is difficult because pages are high-resolution, dense, and complex in layout. Modular pipelines pass errors from one stage to the next. End-to-end VLMs that read whole pages at native resolution spend compute on blank regions, since token cost grows quadratically, and they tend to hallucinate on long inputs. MinerU2.5 is a 1.2B-parameter VLM built on the Qwen2-VL design that handles parsing in two passes within a single model. First, it locates layout elements on a downscaled copy of the page. Then it re-reads each detected region as a crop taken from the original image at native resolution, which preserves fine text, formulas and tables. Training draws on a closed-loop data engine that collects, cleans and synthesizes diverse corpora for pretraining and fine-tuning. The authors report top or near-top results on layout, table and formula benchmarks. It outperforms both general-purpose VLMs and specialized parsers while using far less computation. This makes it a practical option for converting large PDF collections into structured data for LLM and RAG work.

Key points

  • Architecture:
    • Qwen2-Instruct-0.5B decoder with M-RoPE.
    • 675M NaViT vision encoder initialized from Qwen2-VL, using 2D-RoPE without window attention.
    • Pixel-unshuffle patch merger that combines 2×2 vision tokens.
  • Two-stage inference:
    • Stage I analyzes layout on a fixed 1036×1036 thumbnail.
    • Stage II recognizes native-resolution crops, capped at 2048×28×28 pixels.
    • The authors claim roughly an order-of-magnitude compute saving compared with native-resolution end-to-end models.
  • Table recognition:
    • Best result on FinTabNet (TEDS 95.97 / TEDS-S 97.61).
    • Best on the in-house TR benchmark (71.48 / 82.83), slightly ahead of Gemini-2.5 Pro.
    • Competitive on PubTabNet, CC-OCR and OCRBench v2.
  • Formula recognition (CDM metric):
    • Best on 4 of 7 benchmarks, including UniMER-Test SCE (96.4) and the LaTeX-80M matrix subset (90.6).
    • Also best on the in-house Fuzzy Math (92.6) and Complex (82.2) sets.
  • Limitation: errors in Stage I (missed or misclassified regions) cannot be recovered later. The authors identify more diverse training data as the main remedy.

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

 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.Language models & pretraining · 3,320 worksVision & language · 657 works

Cite

Cite as Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang and Conghui He. 2026. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-industry.3

@inproceedings{niu2026mineru2,
  title = {{MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing}},
  author = {Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang and Conghui He},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-industry.3},
  url = {https://doi.org/10.18653/v1/2026.acl-industry.3}
}

References

60 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ling Fu, Zhebin Kuang, Jiajun Song, Mingxin Huang, Biao Yang, Yuzhe Li, Linghao Zhu, Qidi Luo, Xinyu Wang, Hao Lu, and 1 others. 2024. Ocrbench v2: An improved benchmark for evaluating large multimodal models on visual text localization and reasoning. arXiv preprint arXiv:2501.00321. — [arXiv:2501.00321](https://arxiv.org/abs/2501.00321) find
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  3. Dong Guo, Faming Wu, Feida Zhu, Fuxing Leng, Guang Shi, Haobin Chen, Haoqi Fan, Jian Wang, Jianyu Jiang, Jiawei Wang, and 1 others. 2025. Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062. — Seed1.5-VL Technical Report
  4. Haoli Bai, Zhiguang Liu, Xiaojun Meng, Wentao Li, Shuang Liu, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, and 1 others. 2022. Wukong-reader: Multi-modal pre-training for fine-grained visual document understanding. arXiv preprint arXiv:2212.09621. find
  5. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. 2022. Layoutlmv3: Pre-training for document ai with unified text and image masking. In Proceedings of the 30th ACM international conference on multimedia, pages 4083–4091.
  6. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  7. Geewook Kim, Teakgyu Hong, Moonbin Yim, JeongYeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, and Seunghyun Park. 2022. Ocr-free document understanding transformer. In European Conference on Computer Vision, pages 498–517. Springer.
  8. Lukas Blecher, Guillem Cucurull, Thomas Scialom, and Robert Stojnic. 2023. Nougat: Neural optical understanding for academic documents. arXiv preprint arXiv:2308.13418. chatdoc com. 2025. Ocrflux. https://github.com/ chatdoc-com/OCRFlux. Accessed:2025-09-25. ↗
  9. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  10. Song Chen, Xinyu Guo, Yadong Li, Tao Zhang, Mingan Lin, Dongdong Kuang, Youwei Zhang, Lingfeng Ming, Fengyu Zhang, Yuran Wang, and 1 others. 2025. Ocean-ocr: Towards general ocr application via a vision-language model. arXiv preprint arXiv:2501.15558. — [arXiv:2501.15558](https://arxiv.org/abs/2501.15558) find
  11. Zhang Li, Yuliang Liu, Qiang Liu, Zhiyin Ma, Ziyang Zhang, Shuo Zhang, Zidun Guo, Jiarui Zhang, Xinyu Wang, and Xiang Bai. 2025. Monkeyocr: Document parsing with a structure-recognition-relation triplet paradigm. arXiv preprint arXiv:2506.05218. find
  12. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  13. Haofu Liao, Aruni RoyChowdhury, Weijian Li, Ankan Bansal, Yuting Zhang, Zhuowen Tu, Ravi Kumar Satzoda, R Manmatha, and Vijay Mahadevan. 2023. Doctr: Document transformer for structured information extraction in documents. In Proceedings of the IEEE/CVF International Conference on Computer Vision, p… find
  14. Cheng Cui, Ting Sun, Manhui Lin, Tingquan Gao, Yubo Zhang, Jiaxuan Liu, Xueqing Wang, Zelun Zhang, Changda Zhou, Hongen Liu, and 1 others. 2025. Paddleocr 3.0 technical report. arXiv preprint arXiv:2507.05595. — [arXiv:2507.05595](https://arxiv.org/abs/2507.05595) find
  15. Cheng Da, Chuwei Luo, Qi Zheng, and Cong Yao. 2023. Vision grid transformer for document layout analysis. In Proceedings of the IEEE/CVF international conference on computer vision, pages 19462–19472. find
  16. Demiao Lin. 2024. Revolutionizing retrieval-augmented generation with enhanced pdf structure recognition. arXiv preprint arXiv:2401.12599. — [arXiv:2401.12599](https://arxiv.org/abs/2401.12599) find
  17. Chaohu Liu, Kun Yin, Haoyu Cao, Xinghua Jiang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun, and Linli Xu. 2024a. Hrvda: High-resolution visual document assistant. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15534–15545. find
  18. Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim M Alabdulmohsin, and 1 others. 2023. Patch n’pack: Navit, a vision transformer for any aspect ratio and resolution. Advances in Neural Informat… find
  19. Hongen Liu, Cheng Cui, Yuning Du, Yi Liu, and Gang Pan. 2025a. Pp-formulanet: Bridging accuracy and efficiency in advanced formula recognition. arXiv preprint arXiv:2503.18382. — [arXiv:2503.18382](https://arxiv.org/abs/2503.18382) find
  20. Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, and 1 others. 2025. Dolphin: Document image parsing via heterogeneous anchor prompting. arXiv preprint arXiv:2505.14059. find
  21. Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Xiao Zhou, Yang Yu, and 1 others. 2025b. Points-reader: Distillation-free adaptation of vision-language models for document conversion. arXiv preprint arXiv:2509.01215. find
  22. Birgit Pfitzmann, Christoph Auer, Michele Dolfi, Ahmed S Nassar, and Peter Staar. 2022. Doclaynet: A large human-annotated dataset for document-layout segmentation. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pages 3743–3751. find
  23. Yuliang Liu, Biao Yang, Qiang Liu, Zhang Li, Zhiyin Ma, Shuo Zhang, and Xiang Bai. 2024b. Textmonkey: An ocr-free large multimodal model for understanding document. arXiv preprint arXiv:2403.04473. — [arXiv:2403.04473](https://arxiv.org/abs/2403.04473) find
  24. Jake Poznanski, Aman Rangapur, Jon Borchardt, Jason Dunkelberger, Regan Huff, Daniel Lin, Christopher Wilhelm, Kyle Lo, and Luca Soldaini. 2025. olmocr: Unlocking trillions of tokens in pdfs with vision language models. arXiv preprint arXiv:2502.18443.
  25. Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, and 1 others. 2025. Docling: An efficient open-source toolkit for ai-driven document conversion. arXiv preprint arXiv:2501.17887. — [arXiv:2501.17887](https://arxiv.org/abs/2501.17887) find
  26. RapidAI. 2024. Rapid table. https://github.com/ RapidAI/RapidTable. Accessed: 2025-9-25. rednote. 2025. dots.ocr: Multilingual document layout parsing in a single vision-language model. https://github.com/rednote-hilab/ dots.ocr. Accessed:2025-09-25. ↗
  27. Maksym Lysak, Ahmed Nassar, Nikolaos Livathinos, Christoph Auer, and Peter Staar. 2023. Optimized table tokenization for table structure recognition. In International Conference on Document Analysis and Recognition, pages 37–50. Springer. find
  28. Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes Totz, Andrew P Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. 2016. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Proceedings of the IEEE conference on computer vision and patt… find
  29. Souvik Mandalm. 2025. Nanonets-ocr-s. https://nanonets.com/research/nanonets-ocr-s/. Accessed:2025-09-25. ↗
  30. Mathpix. 2025. Mathpix. https://mathpix.com/. Accessed:2025-09-25. ↗
  31. Jianlin Su, Murtadha Ahmed, Yu Lu, Shengfeng Pan, Wen Bo, and Yunfeng Liu. 2024. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing, 568:127063.
  32. Ahmed Nassar, Andres Marafioti, Matteo Omenetti, Maksym Lysak, Nikolaos Livathinos, Christoph Auer, Lucas Morin, Rafael Teixeira de Lima, Yusik Kim, A Said Gurbuz, and 1 others. 2025. Smoldocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion. arXiv preprint a… — [arXiv:2503.11576](https://arxiv.org/abs/2503.11576) find
  33. Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, and Mohit Bansal. 2023. Unifying vision, text, and layout for universal document processing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19254– 19264. find
  34. Junbo Niu, Yuanhong Zheng, Ziyang Miao, Hejun Dong, Chunjiang Ge, Hao Liang, Ma Lu, Bohan Zeng, Qiahao Zheng, Conghui He, and 1 others. 2025. Native visual understanding: Resolving resolution dilemmas in vision-language models. arXiv preprint arXiv:2506.12776. — [arXiv:2506.12776](https://arxiv.org/abs/2506.12776) find
  35. Mistral AI Team. 2025. Mistral-ocr. https://mistral.ai/news/mistral-ocr?utm_source= ai-bot.cn. Accessed:2025-09-25. ↗
  36. Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. find
  37. OpenDataLab. 2025. Pdf-extract-kit. https://github.com/opendatalab/PDF-Extract-Kit. Accessed:2025-09-25. ↗
  38. Jianqiang Wan, Sibo Song, Wenwen Yu, Yuliang Liu, Wenqing Cheng, Fei Huang, Xiang Bai, Cong Yao, and Zhibo Yang. 2024. Omniparser: A unified framework for text spotting key information extraction and table recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognit… find
  39. Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, and 1 others. 2025. Omnidocbench: Benchmarking diverse pdf document parsing with comprehensive annotations. In Proceedings of the Computer Vision and Pattern Recognition Conferen… find
  40. Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, and 1 others. 2024a. Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, 37:107984–108011. find
  41. Vik Paruchuri. 2025. Marker. https://github.com/ datalab-to/marker. Accessed:2025-09-25. ↗
  42. Bin Wang, Zhuangcheng Gu, Guang Liang, Chao Xu, Bo Zhang, Botian Shi, and Conghui He. 2024b. Unimernet: A universal network for real-world mathematical expression recognition. arXiv preprint arXiv:2404.15254. find
  43. Vikas Paruchuri and Datalab Team. 2025. Surya: A lightweight document ocr and analysis toolkit. https://github.com/VikParuchuri/surya. Accessed:2025-09-25. ↗
  44. Bin Wang, Fan Wu, Linke Ouyang, Zhuangcheng Gu, Rui Zhang, Renqiu Xia, Botian Shi, Bo Zhang, and Conghui He. 2025a. Image over text: Transforming formula recognition evaluation with character detection matching. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 19681–19… find
  45. Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, and Wentao Zhang. 2024a. Ocr hinders rag: Evaluating the cascading impact of ocr on retrieval-augmented generation. arXiv preprint arXiv:2412.02592. — [arXiv:2412.02592](https://arxiv.org/abs/2412.02592) find
  46. Qintong Zhang, Bin Wang, Victor Shea-Jay Huang, Junyuan Zhang, Zhengren Wang, Hao Liang, Conghui He, and Wentao Zhang. 2024b. Document parsing unveiled: Techniques, challenges, and prospects for structured information extraction. arXiv preprint arXiv:2410.21169. — [arXiv:2410.21169](https://arxiv.org/abs/2410.21169) find
  47. Bin Wang, Chao Xu, Xiaomeng Zhao, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Rui Xu, Kaiwen Liu, Yuan Qu, Fukai Shang, and 1 others. 2024c. Mineru: An open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839. find
  48. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, and 1 others. 2024d. Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.12191.
  49. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, and Bin Cui. 2024a. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473.
  50. Zhiyuan Zhao, Hengrui Kang, Bin Wang, and Conghui He. 2024b. Doclayout-yolo: Enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. arXiv preprint arXiv:2410.12628. — [arXiv:2410.12628](https://arxiv.org/abs/2410.12628) find
  51. Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, and 1 others. 2025b. Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265.
  52. Xinyi Zheng, Douglas Burdick, Lucian Popa, Xu Zhong, and Nancy Xin Ru Wang. 2021. Global table extractor (gte): A framework for joint table identification and cell structure recognition using visual context. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 6… find
  53. Zilong Wang, Yiheng Xu, Lei Cui, Jingbo Shang, and Furu Wei. 2021. Layoutreader: Pre-training of text and layout for reading order detection. arXiv preprint arXiv:2108.11591. find
  54. Zilong Wang, Yichao Zhou, Wei Wei, Chen-Yu Lee, and Sandeep Tata. 2023. Vrdu: A benchmark for visually-rich document understanding. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5184–5193. find
  55. Xu Zhong, Elaheh ShafieiBavani, and Antonio Jimeno Yepes. 2020. Image-based table recognition: data, model, and evaluation. In European conference on computer vision, pages 564–580. Springer. find
  56. Jinguo Zhu, Weiyun Wang, Zhe Chen, Zhaoyang Liu, Shenglong Ye, Lixin Gu, Hao Tian, Yuchen Duan, Weijie Su, Jie Shao, and 1 others. 2025. Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479.
  57. Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, and 1 others. 2024. General ocr theory: Towards ocr-2.0 via a unified end-to-end model. arXiv preprint arXiv:2409.01704. — [arXiv:2409.01704](https://arxiv.org/abs/2409.01704) find
  58. Zhibo Yang, Jun Tang, Zhaohai Li, Pengfei Wang, Jianqiang Wan, Humen Zhong, Xuejing Liu, Mingkun Yang, Peng Wang, Shuai Bai, and 1 others. 2024. Cc-ocr: A comprehensive and challenging ocr benchmark for evaluating large multimodal models in literacy. arXiv preprint arXiv:2412.02210. — [arXiv:2412.02210](https://arxiv.org/abs/2412.02210) find
  59. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, and 1 others. 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800.
  60. Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, and 15 others. 2025. Minicpm-v 4.5: Cooking efficient mllms…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/