Elamur Research⌕
☰
home / papers / 2026 / STEP3-VL-10B Technical Report

STEP3-VL-10B Technical Report

Paper · 2026 · Ailin Huang, Chengyuan Yao, Chunrui Han et al.

Summary

Compact multimodal models (around 10B parameters or fewer) are usually efficient but weaker at difficult perception and reasoning. STEP3-VL-10B, from StepFun, aims to close this gap. Its architecture joins a 1.8B language-aligned Perception Encoder to a Qwen3-8B decoder. Both components were trained jointly, with no frozen parts, in a single pre-training stage on 1.2T multimodal tokens. This corpus covers knowledge, education, OCR, document parsing, grounding, counting and GUI data. Post-training uses two rounds of supervised finetuning and more than 1k reinforcement learning iterations, combining verifiable rewards (RLVR) and human feedback (RLHF). At inference time, Parallel Coordinated Reasoning (PaCoRe) runs many candidate solutions in parallel, and the model then cross-checks and merges them into a final answer. The authors report that the model matches or beats open models 10–20× its size, such as GLM-4.6V-106B and Qwen3-VL-235B, as well as proprietary systems like Gemini 2.5 Pro. The weights are openly released, giving the community a strong and inexpensive multimodal baseline.

Key points

  • Architecture: A projector with 16× spatial downsampling connects encoder and decoder. Images are split into a 728×728 global view plus 504×504 local crops, and positions use plain 1D RoPE.
  • Pre-training data:
    • roughly 15M education samples spanning K-12, university and professional exams;
    • 10M real and 30M synthetic OCR images;
    • about 80M full-page documents;
    • image-to-code data in LaTeX, Matplotlib, TikZ and Graphviz.
  • Reported scores: 92.2% MMBench, 80.11% MMMU, 94.43% AIME2025 and 75.95% MathVision.
  • PaCoRe gains over sequential reasoning:
    • MathVision +5.14 and DynaMath +5.09;
    • CountQA +4.6 and OCRBench +2.25;
    • All-Angles-Bench +7.50 and SpatialViz-Bench +6.52.
  • Release and future work: Weights are available on Hugging Face and ModelScope. Planned work includes distilling parallel reasoning into faster direct answers and grounding the model in physical, embodied settings.

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 3The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 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 Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun, Jingcheng Hu, Kangheng Lin, Liang Zhao, Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen, Zejia Weng, Ziyang Meng, Ang Li, Aobo Kong, Bo Dong, Changyi Wan, David Wang, Di Qi, Dingming Li, En Yu, Guopeng Li, Haiquan Yin, Han Zhou, Hanshan Zhang, Haolong Yan, Hebin Zhou, Hongbo Peng, Jiaran Zhang, Jiashu Lv, Jiayi Fu, Jie Cheng, Jie Zhou, Jisheng Yin, Jingjing Xie, Jingwei Wu, Jun Zhang, Junfeng Liu, Kaijun Tan, Kaiwen Yan, Liangyu Chen, Lina Chen, Mingliang Li, Qian Zhao, Quan Sun, Shaoliang Pang, Shengjie Fan, Shijie Shang, Siyuan Zhang, Tianhao You, Wei Ji, Wuxun Xie, Xiaobo Yang, Xiaojie Hou, Xiaoran Jiao, Xiaoxiao Ren, Xiangwen Kong, Xin Huang, Xin Wu, Xing Chen, Xinran Wang, Xuelin Zhang, Yana Wei, Yang Li, Yanming Xu, Yeqing Shen, Yuang Peng, Yue Peng, Yu Zhou, Yusheng Li, Yuxiang Yang, Yuyang Zhang, Zhe Xie, Zhewei Huang, Zhenyi Lu, Zhimin Fan, Zihui Cheng, Daxin Jiang, Qi Han, Xiangyu Zhang, Yibo Zhu and Zheng Ge. 2026. STEP3-VL-10B Technical Report. arXiv:2601.09668.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2601.09668 · arXiv 2601.09668

@misc{huang2026step3,
  title = {{STEP3-VL-10B Technical Report}},
  author = {Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun, Jingcheng Hu, Kangheng Lin, Liang Zhao, Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen, Zejia Weng, Ziyang Meng, Ang Li, Aobo Kong, Bo Dong, Changyi Wan, David Wang, Di Qi, Dingming Li, En Yu, Guopeng Li, Haiquan Yin, Han Zhou, Hanshan Zhang, Haolong Yan, Hebin Zhou, Hongbo Peng, Jiaran Zhang, Jiashu Lv, Jiayi Fu, Jie Cheng, Jie Zhou, Jisheng Yin, Jingjing Xie, Jingwei Wu, Jun Zhang, Junfeng Liu, Kaijun Tan, Kaiwen Yan, Liangyu Chen, Lina Chen, Mingliang Li, Qian Zhao, Quan Sun, Shaoliang Pang, Shengjie Fan, Shijie Shang, Siyuan Zhang, Tianhao You, Wei Ji, Wuxun Xie, Xiaobo Yang, Xiaojie Hou, Xiaoran Jiao, Xiaoxiao Ren, Xiangwen Kong, Xin Huang, Xin Wu, Xing Chen, Xinran Wang, Xuelin Zhang, Yana Wei, Yang Li, Yanming Xu, Yeqing Shen, Yuang Peng, Yue Peng, Yu Zhou, Yusheng Li, Yuxiang Yang, Yuyang Zhang, Zhe Xie, Zhewei Huang, Zhenyi Lu, Zhimin Fan, Zihui Cheng, Daxin Jiang, Qi Han, Xiangyu Zhang, Yibo Zhu and Zheng Ge},
  year = {2026},
  doi = {10.48550/arxiv.2601.09668},
  eprint = {2601.09668},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2601.09668}
}

References

145 references, 52 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. aallail. Nyu-book-eval-eg2 dataset. URL https://huggingface.co/datasets/aallail/nyu_book_eval_eg2 . X. An, Y. Xie, K. Yang, W. Zhang, X. Zhao, Z. Cheng, Y. Wang, S. Xu, C. Chen, D. Zhu, et al. Llava-onevision-1.5: Fully open framework for democratized multimodal training. arXiv preprint arXiv:2509.2… — [arXiv:2509.23661](https://arxiv.org/abs/2509.23661) ↗
  2. R. K. Arora, J. Wei, R. S. Hicks, P. Bowman, J. Quiñonero-Candela, F. Tsimpourlas, M. Sharman, M. Shah, A. Vallone, A. Beutel, J. Heidecke, and K. Singhal. Healthbench: Evaluating large language models towards improved human health, 2025. URL https://arxiv.org/abs/2505.08775 . ↗
  3. S. Bai, Y. Cai, R. Chen, K. Chen, X. Chen, Z. Cheng, L. Deng, W. Ding, C. Gao, C. Ge, W. Ge, Z. Guo, Q. Huang, J. Huang, F. Huang, B. Hui, S. Jiang, Z. Li, M. Li, M. Li, K. Li, Z. Lin, J. Lin, X. Liu, J. Liu, C. Liu, Y. Liu, D. Liu, S. Liu, D. Lu, R. Luo, C. Lv, R. Men, L. Meng, X. Ren, X. Ren, S. S… — Qwen3-VL Technical Report
  4. E. Bakouch, L. Ben Allal, A. Lozhkov, N. Tazi, L. Tunstall, C. M. Patiño, E. Beeching, A. Roucher, A. J. Reedi, Q. Gallouédec, K. Rasul, N. Habib, C. Fourrier, H. Kydlicek, G. Penedo, H. Larcher, M. Morlon, V. Srivastav, J. Lochner, X.-S. Nguyen, C. Raffel, L. von Werra, and T. Wolf. SmolLM3: smol,… find
  5. A. Ben Abacha, S. A. Hasan, V. V. Datla, J. Liu, D. Demner-Fushman, and H. Müller. Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In Working Notes of CLEF 2019, volume 2380 of CEUR Workshop Proceedings, Lugano, Switzerland, September 9-12 2019. CEUR-WS.org. URL ht… find
  6. J. Bernstein and L. Newhouse. Old optimizer, new norm: An anthology, 2024. URL https://arxiv.org/abs/2409.20325 . — [arXiv:2409.20325](https://arxiv.org/abs/2409.20325) ↗
  7. D. Bolya, P.-Y. Huang, P. Sun, J. H. Cho, A. Madotto, C. Wei, T. Ma, J. Zhi, J. Rajasegaran, H. Rasheed, et al. Perception encoder: The best visual embeddings are not at the output of the network. arXiv preprint arXiv:2504.13181, 2025. — [arXiv:2504.13181](https://arxiv.org/abs/2504.13181) find
  8. M. Byeon, B. Park, H. Kim, S. Lee, W. Baek, and S. Kim. Coyo-700m: Image-text pair dataset. https://github.com/kakaobrain/coyo-dataset , 2022. ↗
  9. ByteDance-Seed. Beyondaime: Advancing math reasoning evaluation beyond high school olympiads. [https://huggingface.co/datasets/ByteDance-Seed/BeyondAIME ](https://huggingface.co/datasets/ByteDance-Seed/BeyondAIME) , 2025. find
  10. M. Caron, I. Misra, J. Mairal, P. Goyal, P. Bojanowski, and A. Joulin. Unsupervised learning of visual features by contrasting cluster assignments, 2021. URL https://arxiv.org/abs/2006.09882 . — [arXiv:2006.09882](https://arxiv.org/abs/2006.09882) ↗
  11. M. Chai, Z. Shen, C. Zhang, Y. Zhang, X. Wang, S. Dou, J. Kang, J. Zhang, and Q. Zhang. Docfusion: A unified framework for document parsing tasks, 2025. URL https://arxiv.org/abs/2412.12505 . ↗
  12. J. Chen, L. Kong, H. Wei, C. Liu, Z. Ge, L. Zhao, J. Sun, C. Han, and X. Zhang. Onechart: Purify the chart structural extraction via one auxiliary token. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 147–155, 2024a. find
  13. L. Chen, J. Li, X. Dong, P. Zhang, Y. Zang, Z. Chen, H. Duan, J. Wang, Y. Qiao, D. Lin, et al. Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330, 2024b.
  14. X. Cheng, W. Zhang, S. Zhang, J. Yang, X. Guan, X. Wu, X. Li, G. Zhang, J. Liu, Y. Mai, Y. Zeng, Z. Wen, K. Jin, B. Wang, W. Zhou, Y. Lu, T. Li, W. Huang, and Z. Li. Simplevqa: Multimodal factuality evaluation for multimodal large language models, 2025. URL https://arxiv.org/abs/2502.13059 . — [arXiv:2502.13059](https://arxiv.org/abs/2502.13059) ↗
  15. W.-L. Chiang, L. Zheng, Y. Sheng, A. N. Angelopoulos, T. Li, D. Li, H. Zhang, B. Zhu, M. Jordan, J. E. Gonzalez, and I. Stoica. Chatbot arena: An open platform for evaluating llms by human preference, 2024.
  16. C. Chou, L. Dunlap, K. Mashita, K. Mandal, T. Darrell, I. Stoica, J. E. Gonzalez, and W.-L. Chiang. Visionarena: 230k real world user-vlm conversations with preference labels. 2024. URL https://arxiv.org/abs/2412.08687 . ↗
  17. CNMO Committee. Chinese national mathematical olympiad (cnmo), 2024. Accessed: 2025. find
  18. CommonCrawl. Common crawl. URL https://commoncrawl.org/ . C. Cui, T. Sun, M. Lin, T. Gao, Y. Zhang, J. Liu, X. Wang, Z. Zhang, C. Zhou, H. Liu, Y. Zhang, W. Lv, K. Huang, Y. Zhang, J. Zhang, J. Zhang, Y. Liu, D. Yu, and Y. Ma. Paddleocr 3.0 technical report, 2025a. URL https://arxiv.org/abs/2507.055… — [arXiv:2507.05595](https://arxiv.org/abs/2507.05595) ↗
  19. G. Cui, Y. Zhang, J. Chen, L. Yuan, Z. Wang, Y. Zuo, H. Li, Y. Fan, H. Chen, W. Chen, et al. The entropy mechanism of reinforcement learning for reasoning language models. arXiv preprint arXiv:2505.22617, 2025b. find
  20. M. Deitke, C. Clark, S. Lee, R. Tripathi, Y. Yang, J. S. Park, M. Salehi, N. Muennighoff, K. Lo, L. Soldaini, J. Lu, T. Anderson, E. Bransom, K. Ehsani, H. Ngo, Y. Chen, A. Patel, M. Yatskar, C. Callison-Burch, A. Head, R. Hendrix, F. Bastani, E. VanderBilt, N. Lambert, Y. Chou, A. Chheda, J. Sparks… — Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
  21. S. Ding, S. Wu, X. Zhao, Y. Zang, H. Duan, X. Dong, P. Zhang, Y. Cao, D. Lin, and J. Wang. Mm-ifengine: Towards multimodal instruction following. arXiv preprint arXiv:2504.07957, 2025. — [arXiv:2504.07957](https://arxiv.org/abs/2504.07957) find
  22. R.-Z. Fan, Z. Wang, and P. Liu. Megascience: Pushing the frontiers of post-training datasets for science reasoning. arXiv preprint arXiv:2507.16812, 2025. — [arXiv:2507.16812](https://arxiv.org/abs/2507.16812) find
  23. X. Fu, Y. Hu, B. Li, Y. Feng, H. Wang, X. Lin, D. Roth, N. A. Smith, W.-C. Ma, and R. Krishna. Blink: Multimodal large language models can see but not perceive. In European Conference on Computer Vision, pages 148–166. Springer, 2024. find
  24. T. Guan, F. Liu, X. Wu, R. Xian, Z. Li, X. Liu, X. Wang, L. Chen, F. Huang, Y. Yacoob, et al. Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Patter…
  25. E. Guha, R. Marten, S. Keh, N. Raoof, G. Smyrnis, H. Bansal, M. Nezhurina, J. Mercat, T. Vu, Z. Sprague, A. Suvarna, B. Feuer, L. Chen, Z. Khan, E. Frankel, S. Grover, C. Choi, N. Muennighoff, S. Su, W. Zhao, J. Yang, S. Pimpalgaonkar, K. Sharma, C. C.-J. Ji, Y. Deng, S. Pratt, V. Ramanujan, J. Saad… — OpenThoughts: Data Recipes for Reasoning Models
  26. D. Guo, F. Wu, F. Zhu, F. Leng, G. Shi, H. Chen, H. Fan, J. Wang, J. Jiang, J. Wang, et al. Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062, 2025a.
  27. D. Guo, D. Yang, H. Zhang, J. Song, R. Zhang, R. Xu, Q. Zhu, S. Ma, P. Wang, X. Bi, et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948, 2025b.
  28. X. He, Y. Zhang, L. Mou, E. Xing, and P. Xie. Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286, 2020. — [arXiv:2003.10286](https://arxiv.org/abs/2003.10286) find
  29. HMMT. Hmmt 2025, 2025. URL https://www.hmmt.org/ . Accessed: 2025. ↗
  30. J. Hu, Y. Zhang, Q. Han, D. Jiang, X. Zhang, and H.-Y. Shum. Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model. arXiv preprint arXiv:2503.24290, 2025.
  31. J. Hu, Y. Zhang, S. Shang, X. Yang, Y. Peng, Z. Huang, H. Zhou, X. Wu, J. Cheng, F. Wan, X. Kong, C. Yao, K. Yan, A. Huang, H. Zhou, Q. Han, Z. Ge, D. Jiang, X. Zhang, and H.-Y. Shum. Pacore: Learning to scale test-time compute with parallel coordinated reasoning, 2026. URL https://arxiv.org/abs/260… ↗
  32. N. Jain, K. Han, A. Gu, W.-D. Li, F. Yan, T. Zhang, S. Wang, A. Solar-Lezama, K. Sen, and I. Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.07974, 2024.
  33. M. Jia, Z. Qi, S. Zhang, W. Zhang, X. Yu, J. He, H. Wang, and L. Yi. Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models, 2025. URL https://arxiv.org/abs/2506.03135 . — [arXiv:2506.03135](https://arxiv.org/abs/2506.03135) ↗
  34. A. Jian, W. Qiu, X. Wang, P. Wang, Y. Hao, J. Pei, Y. Wei, Y. Peng, and X. Song. Csvqa: A chinese multimodal benchmark for evaluating stem reasoning capabilities of vlms, 2025. URL https://arxiv.org/abs/2505.24120 . — [arXiv:2505.24120](https://arxiv.org/abs/2505.24120) ↗
  35. Kaggle. Fcs dataset. URL https://www.kaggle.com/datasets/xuncngng/fsc147-0 . D. Kahneman. Thinking, fast and slow. Farrar, Straus and Giroux, 2011. ↗
  36. A. Kanade and T. Ganu. Do you see me : A multidimensional benchmark for evaluating visual perception in multimodal llms, 2025. URL https://arxiv.org/abs/2506.02022 . ↗
  37. M. Kazemi, N. Dikkala, A. Anand, P. Devic, I. Dasgupta, F. Liu, B. Fatemi, P. Awasthi, D. Guo, S. Gollapudi, and A. Qureshi. Remi: A dataset for reasoning with multiple images, 2024. URL https://arxiv.org/abs/2406.09175 . — [arXiv:2406.09175](https://arxiv.org/abs/2406.09175) ↗
  38. J. Keller. Muon: An optimizer for hidden layers in neural networks, 2024. URL https://kellerjordan.github.io/posts/muon/ . ↗
  39. A. Kembhavi, M. Salvato, E. Kolve, M. Seo, H. Hajishirzi, and A. Farhadi. A diagram is worth a dozen images, 2016. URL https://arxiv.org/abs/1603.07396 . ↗
  40. G. Kim, T. Hong, M. Yim, J. Nam, J. Park, J. Yim, W. Hwang, S. Yun, D. Han, and S. Park. Ocr-free document understanding transformer. In European Conference on Computer Vision (ECCV), 2022.
  41. A. Kuznetsova, H. Rom, N. Alldrin, J. Uijlings, I. Krasin, J. Pont-Tuset, S. Kamali, S. Popov, M. Malloci, A. Kolesnikov, T. Duerig, and V. Ferrari. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. International Journal of Comput… — [doi:10.1007/s112](https://doi.org/10.1007/s112) find
  42. H. Laurençon, L. Tronchon, and V. Sanh. Unlocking the conversion of web screenshots into html code with the websight dataset, 2024. find
  43. D. Li, H. Li, Z. Wang, Y. Yan, H. Zhang, S. Chen, G. Hou, S. Jiang, W. Zhang, Y. Shen, W. Lu, and Y. Zhuang. Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models, 2025a. URL https://arxiv.org/abs/2505.21500 . — [arXiv:2505.21500](https://arxiv.org/abs/2505.21500) ↗
  44. J. Li, D. Li, C. Xiong, and S. Hoi. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation, 2022. URL https://arxiv.org/abs/22 01.12086 . ↗
  45. J. LI, E. Beeching, L. Tunstall, B. Lipkin, R. Soletskyi, S. C. Huang, K. Rasul, L. Yu, A. Jiang, Z. Shen, Z. Qin, B. Dong, L. Zhou, Y. Fleureau, G. Lample, and S. Polu. Numinamath. [https://huggingface.co/AI-MO/NuminaMath-1.5](https://github.com/pro ject-numina/aimo-progress-prize/blob/main/report/… find
  46. K. Li, Z. Meng, H. Lin, Z. Luo, Y. Tian, J. Ma, Z. Huang, and T.-S. Chua. Screenspot-pro: Gui grounding for professional high-resolution computer use, 2025b. URL https://arxiv.org/abs/2504.07981 . — [arXiv:2504.07981](https://arxiv.org/abs/2504.07981) ↗
  47. L. Li, M. Bigverdi, J. Gu, Z. Ma, Y. Yang, Z. Li, Y. Choi, and R. Krishna. Unfolding spatial cognition: Evaluating multimodal models on visual simulations, 2025c. URL https://arxi v.org/abs/2506.04633 . find
  48. T. Li, W.-L. Chiang, E. Frick, L. Dunlap, T. Wu, B. Zhu, J. E. Gonzalez, and I. Stoica. From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline, 2024. URL https://arxiv.org/abs/2406.11939 . ↗
  49. Y. Li, Q. Gao, T. Zhao, B. Wang, H. Sun, H. Lyu, R. D. Hawkins, N. Vasconcelos, T. Golan, D. Luo, and H. Deng. Core knowledge deficits in multi-modal language models, 2025d. URL https://arxiv.org/abs/2410.10855 . — [arXiv:2410.10855](https://arxiv.org/abs/2410.10855) ↗
  50. B. Y. Lin, Y. Deng, K. Chandu, F. Brahman, A. Ravichander, V. Pyatkin, N. Dziri, R. L. Bras, and Y. Choi. Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024. URL https://arxiv.org/abs/2406.04770 . ↗
  51. T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, J. Hays, P. Perona, D. Ramanan, C. L. Zitnick, and P. Dollár. Microsoft coco: Common objects in context, 2015. URL https://arxiv.org/abs/1405.0312 . ↗
  52. C. Liu, H. Wei, J. Chen, L. Kong, Z. Ge, Z. Zhu, L. Zhao, J. Sun, C. Han, and X. Zhang. Focus anywhere for fine-grained multi-page document understanding. arXiv preprint arXiv:2405.14295, 2024a. — [arXiv:2405.14295](https://arxiv.org/abs/2405.14295) find
  53. J. Liu, J. Su, X. Yao, Z. Jiang, G. Lai, Y. Du, Y. Qin, W. Xu, E. Lu, J. Yan, Y. Chen, H. Zheng, Y. Liu, S. Liu, B. Yin, W. He, H. Zhu, Y. Wang, J. Wang, M. Dong, Z. Zhang, Y. Kang, H. Zhang, X. Xu, Y. Zhang, Y. Wu, X. Zhou, and Z. Yang. Muon is scalable for llm training, 2025a. URL https://arxiv.or… ↗
  54. X. Liu, W. Wang, Y. Yuan, J. tse Huang, Q. Liu, P. He, and Z. Tu. Insight over sight: Exploring the vision-knowledge conflicts in multimodal llms, 2025b. URL https://arxiv.org/abs/2410.08145 . ↗
  55. Y. Liu, H. Duan, Y. Zhang, B. Li, S. Zhang, W. Zhao, Y. Yuan, J. Wang, C. He, Z. Liu, et al. Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233. Springer, 2024b.
  56. Y. Liu, Z. Li, M. Huang, B. Yang, W. Yu, C. Li, X.-C. Yin, C.-L. Liu, L. Jin, and X. Bai. Ocrbench: on the hidden mystery of ocr in large multimodal models. Science China Information Sciences, 67(12), Dec. 2024c. ISSN 1869-1919. doi: 10.1007/s11432-024-4235-6. URL http://dx.doi .org/10.1007/s11432-0… ↗
  57. I. Loshchilov and F. Hutter. arXiv:1711.05101, 2017. find
  58. Decoupled weight decay regularization. P. Lu, H. Bansal, T. Xia, J. Liu, C. Li, H. Hajishirzi, H. Cheng, K.-W. Chang, M. Galley, and J. Gao. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255, 2023.
  59. T. Luong, D. Hwang, H. H. Nguyen, G. Ghiasi, Y. Chervonyi, I. Seo, J. Kim, G. Bingham, J. Lee, S. Mishra, A. Zhai, C. H. Hu, H. Michalewski, J. Kim, J. Ahn, J. Bae, X. Song, T. H. Trinh, Q. V. Le, and J. Jung. Towards robust mathematical reasoning, 2025. URL https://arxiv.org/abs/2511.01846 . ↗
  60. MAA. American invitational mathematics examination 2024, a. find
  61. MAA. American invitational mathematics examination 2025, b. find
  62. A. Masry, P. Kavehzadeh, X. L. Do, E. Hoque, and S. Joty. Unichart: A universal vision-language pretrained model for chart comprehension and reasoning, 2023.
  63. L. Meng, J. Yang, R. Tian, X. Dai, Z. Wu, J. Gao, and Y.-G. Jiang. Deepstack: Deeply stacking visual tokens is surprisingly simple and effective for lmms. Advances in Neural Information Processing Systems, 37:23464–23487, 2024. find
  64. OmniAI. Omni ocr benchmark. URL https://getomni.ai/blog/ocr-benchmark . arXiv preprint OpenAI. Introducing gpt-5.2, 2025a. URL https://openai.com/index/introducing-gpt -5-2/ . ↗
  65. OpenAI. Gpt-oss-120b and gpt-oss-20b model card. arXiv preprint arXiv:2508.10925, 2025b. URL https://arxiv.org/abs/2508.10925 . ↗
  66. OpenAI. Introducing openai o3 and o4-mini. https://openai.com/index/introducing -o3-and-o4-mini/ , 2025c. ↗
  67. L. Ouyang, Y. Qu, H. Zhou, J. Zhu, R. Zhang, Q. Lin, B. Wang, Z. Zhao, M. Jiang, X. Zhao, J. Shi, F. Wu, P. Chu, M. Liu, Z. Li, C. Xu, B. Zhang, B. Shi, Z. Tu, and C. He. Omnidocbench: Benchmarking diverse pdf document parsing with comprehensive annotations, 2024. URL https://arxiv.org/abs/2412.0762… — [arXiv:2412.07626](https://arxiv.org/abs/2412.07626) ↗
  68. R. Paiss, A. Ephrat, O. Tov, S. Zada, I. Mosseri, M. Irani, and T. Dekel. Teaching clip to count to ten, 2023. URL https://arxiv.org/abs/2302.12066 . — [arXiv:2302.12066](https://arxiv.org/abs/2302.12066) ↗
  69. J. Poznanski, A. Rangapur, J. Borchardt, J. Dunkelberger, R. Huff, D. Lin, A. Rangapur, C. Wilhelm, K. Lo, and L. Soldaini. olmocr: Unlocking trillions of tokens in pdfs with vision language models, 2025. URL https://arxiv.org/abs/2502.18443 . ↗
  70. V. Pyatkin, S. Malik, V. Graf, H. Ivison, S. Huang, P. Dasigi, N. Lambert, and H. Hajishirzi. Generalizing verifiable instruction following, 2025.
  71. Y. Qian, H. Ye, J.-P. Fauconnier, P. Grasch, Y. Yang, and Z. Gan. Mia-bench: Towards better instruction following evaluation of multimodal llms, 2025. URL https://arxiv.org/abs/2407.01509 . — [arXiv:2407.01509](https://arxiv.org/abs/2407.01509) ↗
  72. R. Qiao, Q. Tan, G. Dong, M. Wu, C. Sun, X. Song, Z. GongQue, S. Lei, Z. Wei, M. Zhang, et al. We-math: Does your large multimodal model achieve human-like mathematical reasoning? arXiv preprint arXiv:2407.01284, 2024. find
  73. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever. Learning transferable visual models from natural language supervision, 2021. URL https://arxiv.org/abs/2103.00020 . ↗
  74. D. Rein, B. L. Hou, A. C. Stickland, J. Petty, R. Y. Pang, J. Dirani, J. Michael, and S. R. Bowman. Gpqa: A graduate-level google-proof q&a benchmark. arXiv preprint arXiv:2311.12022, 2023.
  75. S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks, 2016. URL https://arxiv.org/abs/1506.01497 . ↗
  76. J. Roberts, M. R. Taesiri, A. Sharma, A. Gupta, S. Roberts, I. Croitoru, S.-V. Bogolin, J. Tang, F. Langer, V. Raina, V. Raina, H. Xiong, V. Udandarao, J. Lu, S. Chen, S. Purkis, T. Yan, W. Lin, G. Shin, Q. Yang, A. T. Nguyen, D. I. Atkinson, A. Baranwal, A. Coca, M. Dang, S. Dziadzio, J. D. Kunz, K… — [arXiv:2502.09696](https://arxiv.org/abs/2502.09696) find
  77. SakiRinn. Locount dataset. URL — LAION-5B: An open large-scale dataset for training next generation image-text models https://github.com/SakiRinn/mmdetection-locount . C. Schuhmann, R. Beaumont, R. Vencu, C. Gordon, R. Wightman, M. Cherti, T. Coombes, A. Katta, C. Mullis, M. Wortsman, P. Schramowski, S. Kundurthy, K. Crowson, L. Schmidt, R. Kaczmarczyk, and J. Jitsev. Laion-5b: An ope… ↗
  78. J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438, 2015. find
  79. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017. find
  80. J. Shah, G. Bikshandi, Y. Zhang, V. Thakkar, P. Ramani, and T. Dao. Flashattention-3: Fast and accurate attention with asynchrony and low-precision. Advances in Neural Information Processing Systems, 37:68658–68685, 2024.
  81. H. Shen, T. Wu, Q. Han, Y. Hsieh, J. Wang, Y. Zhang, Y. Cheng, Z. Hao, Y. Ni, X. Wang, et al. Phyx: Does your model have the" wits" for physical reasoning? arXiv preprint arXiv:2505.15929, 2025. — [arXiv:2505.15929](https://arxiv.org/abs/2505.15929) find
  82. B. Shi, C. Yao, M. Liao, M. Yang, P. Xu, L. Cui, S. Belongie, S. Lu, and X. Bai. Icdar2017 competition on reading chinese text in the wild (rctw-17). In 2017 14th iapr international conference on document analysis and recognition (ICDAR), volume 1, pages 1429–1434. find
  83. C. Si, Y. Zhang, R. Li, Z. Yang, R. Liu, and D. Yang. Design2code: Benchmarking multimodal code generation for automated front-end engineering, 2025. URL https://arxiv.org/ab s/2403.03163 . ↗
  84. O. Siméoni, H. V. Vo, M. Seitzer, F. Baldassarre, M. Oquab, C. Jose, V. Khalidov, M. Szafraniec, S. Yi, M. Ramamonjisoa, F. Massa, D. Haziza, L. Wehrstedt, J. Wang, T. Darcet, T. Moutakanni, L. Sentana, C. Roberts, A. Vedaldi, J. Tolan, J. Brandt, C. Couprie, J. Mairal, H. Jégou, P. Labatut, and P.… — [arXiv:2508.10104](https://arxiv.org/abs/2508.10104) find
  85. V. Sirdeshmukh, K. Deshpande, J. Mols, L. Jin, E.-Y. Cardona, D. Lee, J. Kritz, W. Primack, S. Yue, and C. Xing. Multichallenge: A realistic multi-turn conversation evaluation benchmark challenging to frontier llms, 2025. URL https://arxiv.org/abs/2501.17399 . ↗
  86. W. Song, Y. Li, J. Xu, G. Wu, L. Ming, K. Yi, W. Luo, H. Li, Y. Du, F. Guo, and K. Yu. M3gia: A cognition inspired multilingual and multimodal general intelligence ability benchmark, 2024. URL https://arxiv.org/abs/2406.05343 . — [arXiv:2406.05343](https://arxiv.org/abs/2406.05343) ↗
  87. J. Su, M. Ahmed, Y. Lu, S. Pan, W. Bo, and Y. Liu. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing, 568:127063, 2024.
  88. H. R. Sujet AI, Allaa Boutaleb. Sujet-finance-qa-vision-100k: A large-scale dataset for financial document vqa, 2024. URL https://huggingface.co/datasets/sujet-ai/Sujet-Fin ance-QA-Vision-100k . ↗
  89. J. S. Tamarapalli, R. Grover, N. Pande, and S. Yerramilli. Countqa: How well do mllms count in the wild?, 2025. URL https://arxiv.org/abs/2508.06585 . ↗
  90. K. Tang, W.-L. Chiang, and A. N. Angelopoulos. Arena explorer: A topic modeling pipeline for llm evals & analytics, 2025. find
  91. C. Team, Z. Yue, Z. Lin, Y. Song, W. Wang, S. Ren, S. Gu, S. Li, P. Li, L. Zhao, L. Li, K. Bao, H. Tian, H. Zhang, G. Wang, D. Zhu, Cici, C. He, B. Ye, B. Shen, Z. Zhang, Z. Jiang, Z. Zheng, Z. Song, Z. Luo, Y. Yu, Y. Wang, Y. Tian, Y. Tu, Y. Yan, Y. Huang, X. Wang, X. Xu, X. Song, X. Zhang, X. Yong… — MiMo-VL Technical Report
  92. G. Team. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities, 2025a. URL https://arxiv.org/abs/2507.062 61 . ↗
  93. G. Team. Gemini 3 pro: the frontier of vision ai, 2025b. URL https://blog.google/techno logy/developers/gemini-3-pro-vision/ . ↗
  94. G. R. Team, S. Abeyruwan, J. Ainslie, J.-B. Alayrac, M. G. Arenas, T. Armstrong, A. Balakrishna, R. Baruch, M. Bauza, M. Blokzijl, S. Bohez, K. Bousmalis, A. Brohan, T. Buschmann, A. Byravan, S. Cabi, K. Caluwaerts, F. Casarini, O. Chang, J. E. Chen, X. Chen, H.-T. L. Chiang, K. Choromanski, D. D’Am… find
  95. H. Team. Humanity’s last exam, 2025c. URL https://arxiv.org/abs/2501.14249 . ↗
  96. M.-A.-P. Team, X. Du, Y. Yao, K. Ma, B. Wang, T. Zheng, K. Zhu, M. Liu, Y. Liang, X. Jin, Z. Wei, C. Zheng, K. Deng, S. Guo, S. Jia, S. Jiang, Y. Liao, R. Li, Q. Li, S. Li, Y. Li, Y. Li, D. Ma, Y. Ni, H. Que, Q. Wang, Z. Wen, S. Wu, T. Xing, M. Xu, Z. Yang, Z. M. Wang, J. Zhou, Y. Bai, X. Bu, C. Cai… find
  97. S. Team. Step-3 is large yet affordable: Model-system co-design for cost-effective decoding, 2025d. URL https://arxiv.org/abs/2507.19427 . ↗
  98. V. Team, W. Hong, W. Yu, X. Gu, G. Wang, G. Gan, H. Tang, J. Cheng, J. Qi, J. Ji, L. Pan, S. Duan, W. Wang, Y. Wang, Y. Cheng, Z. He, Z. Su, Z. Yang, Z. Pan, A. Zeng, B. Wang, B. Chen, B. Shi, C. Pang, C. Zhang, D. Yin, F. Yang, G. Chen, J. Xu, J. Zhu, J. Chen, J. Chen, J. Chen, J. Lin, J. Wang, J.… — GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
  99. P. Tong, E. Brown, P. Wu, S. Woo, A. J. V. IYER, S. C. Akula, S. Yang, J. Yang, M. Middepogu, Z. Wang, et al. Cambrian-1: A fully open, vision-centric exploration of multimodal llms. Advances in Neural Information Processing Systems, 37:87310–87356, 2024a.
  100. S. Tong, E. Brown, P. Wu, S. Woo, M. Middepogu, S. C. Akula, J. Yang, S. Yang, A. Iyer, X. Pan, Z. Wang, R. Fergus, Y. LeCun, and S. Xie. Cambrian-1: A fully open, vision-centric exploration of multimodal llms, 2024b. URL https://arxiv.org/abs/2406.16860 . ↗
  101. S. Tong, Z. Liu, Y. Zhai, Y. Ma, Y. LeCun, and S. Xie. Eyes wide shut? exploring the visual shortcomings of multimodal llms, 2024c. URL https://arxiv.org/abs/2401.06209 . ↗
  102. B. Wang, C. Xu, X. Zhao, L. Ouyang, F. Wu, Z. Zhao, R. Xu, K. Liu, Y. Qu, F. Shang, B. Zhang, L. Wei, Z. Sui, W. Li, B. Shi, Y. Qiao, D. Lin, and C. He. Mineru: An open-source solution for precise document content extraction, 2024a. URL https://arxiv.org/abs/2409.18839 . ↗
  103. K. Wang, J. Pan, W. Shi, Z. Lu, M. Zhan, and H. Li. Measuring multimodal mathematical reasoning with math-vision dataset, 2024b. URL https://arxiv.org/abs/2402.14804 . ↗
  104. S. Wang, L. Sun, C. Deng, K. Shao, M. Pei, Z. Tian, H. Zhang, and J. Wang. Spatialviz-bench: Automatically generated spatial visualization reasoning tasks for mllms. arXiv e-prints, pages arXiv–2507, 2025a. find
  105. W. Wang, Z. Gao, L. Gu, H. Pu, L. Cui, X. Wei, Z. Liu, L. Jing, S. Ye, J. Shao, Z. Wang, Z. Chen, H. Zhang, G. Yang, H. Wang, Q. Wei, J. Yin, W. Li, E. Cui, G. Chen, Z. Ding, C. Tian, Z. Wu, J. Xie, Z. Li, B. Yang, Y. Duan, X. Wang, Z. Hou, H. Hao, T. Zhang, S. Li, X. Zhao, H. Duan, N. Deng, B. Fu,… — InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
  106. X. Wang, Z. Wu, J. Xie, Z. Ding, B. Yang, Z. Li, Z. Liu, Q. Li, X. Dong, Z. Chen, W. Wang, X. Zhao, J. Chen, H. Duan, T. Xie, C. Yang, S. Su, Y. Yu, Y. Huang, Y. Liu, X. Zhang, Y. Zhang, X. Yue, W. Su, X. Zhu, W. Shen, J. Dai, and W. Wang. Mmbench-gui: Hierarchical multi-platform evaluation framewor… — [arXiv:2507.19478](https://arxiv.org/abs/2507.19478) find
  107. Y. Wang, X. Ma, G. Zhang, Y. Ni, A. Chandra, S. Guo, W. Ren, A. Arulraj, X. He, Z. Jiang, T. Li, M. Ku, K. Wang, A. Zhuang, R. Fan, X. Yue, and W. Chen. Mmlu-pro: A more robust and challenging multi-task language understanding benchmark. In Advances in Neural Information Processing Systems, NeurIPS…
  108. Z. Wang, M. Xia, L. He, H. Chen, Y. Liu, R. Zhu, K. Liang, X. Wu, H. Liu, S. Malladi, A. Chevalier, S. Arora, and D. Chen. Charxiv: Charting gaps in realistic chart understanding in multimodal llms, 2024d. URL https://arxiv.org/abs/2406.18521 . ↗
  109. Z. Wang, F. Zhou, X. Li, and P. Liu. Octothinker: Mid-training incentivizes reinforcement learning scaling. arXiv preprint arXiv:2506.20512, 2025d. — [arXiv:2506.20512](https://arxiv.org/abs/2506.20512) find
  110. H. Wei, C. Liu, J. Chen, J. Wang, L. Kong, Y. Xu, Z. Ge, L. Zhao, J. Sun, Y. Peng, et al. General ocr theory: Towards ocr-2.0 via a unified end-to-end model. arXiv preprint arXiv:2409.01704, 2024. — [arXiv:2409.01704](https://arxiv.org/abs/2409.01704) find
  111. H. Wei, Y. Sun, and Y. Li. Deepseek-ocr: Contexts optical compression, 2025a. URL https://arxiv.org/abs/2510.18234 . ↗
  112. Y. Wei, L. Zhao, K. Lin, E. Yu, Y. Peng, R. Dong, J. Sun, H. Wei, Z. Ge, X. Zhang, et al. Perception in reflection. arXiv preprint arXiv:2504.07165, 2025b. — [arXiv:2504.07165](https://arxiv.org/abs/2504.07165) find
  113. Y. Wei, L. Zhao, J. Sun, K. Lin, J. Yin, J. Hu, Y. Zhang, E. Yu, H. Lv, Z. Weng, et al. Open vision reasoner: Transferring linguistic cognitive behavior for visual reasoning. arXiv preprint arXiv:2507.05255, 2025c. — [arXiv:2507.05255](https://arxiv.org/abs/2507.05255) find
  114. C. White, S. Dooley, M. Roberts, A. Pal, B. Feuer, S. Jain, R. Shwartz-Ziv, N. Jain, K. Saifullah, S. Dey, Shubh-Agrawal, S. S. Sandha, S. V. Naidu, C. Hegde, Y. LeCun, T. Goldstein, W. Neiswanger, and M. Goldblum. Livebench: A challenging, contamination-free LLM benchmark. In The Thirteenth Interna… find
  115. L. Wiedmann, O. Zohar, A. Mahla, X. Wang, R. Li, T. Frere, L. von Werra, A. R. Gosthipaty, and A. Marafioti. Finevision: Open data is all you need. arXiv preprint arXiv:2510.17269, 2025. — [arXiv:2510.17269](https://arxiv.org/abs/2510.17269) find
  116. P. Wu and S. Xie. V*: Guided visual search as a core mechanism in multimodal llms. arXiv preprint arXiv:2312.14135, 2023. find
  117. Z. Wu, Z. Wu, F. Xu, Y. Wang, Q. Sun, C. Jia, K. Cheng, Z. Ding, L. Chen, P. P. Liang, et al. Os-atlas: A foundation action model for generalist gui agents. arXiv preprint arXiv:2410.23218, 2024.
  118. X.AI. Grok-2 beta release. https://x.ai/blog/grok-2 , 2024. Accessed on: 2024-07-02. ↗
  119. R. Xia, B. Zhang, H. Peng, H. Ye, X. Yan, P. Ye, B. Shi, J. Yan, and Y. Qiao. Structchart: Perception, structuring, reasoning for visual chart understanding. arXiv preprint arXiv:2309.11268, 2023. — [arXiv:2309.11268](https://arxiv.org/abs/2309.11268) find
  120. Y. Xiao, E. Sun, T. Liu, and W. Wang. Logicvista: Multimodal llm logical reasoning benchmark in visual contexts, 2024. URL https://arxiv.org/abs/2407.04973 . — [arXiv:2407.04973](https://arxiv.org/abs/2407.04973) ↗
  121. C. Xie, H. Cai, J. Li, F. Kong, X. Wu, J. Song, H. Morimitsu, L. Yao, D. Wang, X. Zhang, D. Leng, B. Zhang, X. Ji, and Y. Deng. Ccmb: A large-scale chinese cross-modal benchmark. In Proceedings of the 31st ACM International Conference on Multimedia, page 4219–4227. ACM, Oct. 2023. doi: 10.1145/35817… — [doi:10.1145/3581783.3611877](https://doi.org/10.1145/3581783.3611877) find
  122. T. Xie, J. Deng, X. Li, J. Yang, H. Wu, J. Chen, W. Hu, X. Wang, Y. Xu, Z. Wang, Y. Xu, J. Wang, D. Sahoo, T. Yu, and C. Xiong. Scaling computer-use grounding via user interface decomposition and synthesis, 2025. URL https://arxiv.org/abs/2505.13227 . ↗
  123. W. Xu, J. Wang, W. Wang, Z. Chen, W. Zhou, A. Yang, L. Lu, H. Li, X. Wang, X. Zhu, W. Wang, J. Dai, and J. Zhu. Visulogic: A benchmark for evaluating visual reasoning in multi-modal large language models, 2025. URL https://arxiv.org/abs/2504.15279 . — [arXiv:2504.15279](https://arxiv.org/abs/2504.15279) ↗
  124. H. Yan, J. Wang, X. Huang, Y. Shen, Z. Meng, Z. Fan, K. Tan, J. Gao, L. Shi, M. Yang, et al. Step-gui technical report. arXiv preprint arXiv:2512.15431, 2025. — [arXiv:2512.15431](https://arxiv.org/abs/2512.15431) find
  125. A. Yang, A. Li, B. Yang, B. Zhang, B. Hui, B. Zheng, B. Yu, C. Gao, C. Huang, C. Lv, C. Zheng, D. Liu, F. Zhou, F. Huang, F. Hu, H. Ge, H. Wei, H. Lin, J. Tang, J. Yang, J. Tu, J. Zhang, J. Yang, J. Yang, J. Zhou, J. Zhou, J. Lin, K. Dang, K. Bao, K. Yang, L. Yu, L. Deng, M. Li, M. Xue, M. Li, P. Zh… — Qwen3 Technical Report
  126. S. Yang, R. Xu, Y. Xie, S. Yang, M. Li, J. Lin, C. Zhu, X. Chen, H. Duan, X. Yue, D. Lin, T. Wang, and J. Pang. Mmsi-bench: A benchmark for multi-image spatial intelligence, 2025b. URL https://arxiv.org/abs/2505.23764 . — [arXiv:2505.23764](https://arxiv.org/abs/2505.23764) ↗
  127. Y. Yang, A. Patel, M. Deitke, T. Gupta, L. Weihs, A. Head, M. Yatskar, C. Callison-Burch, R. Krishna, A. Kembhavi, and C. Clark. Scaling text-rich image understanding via code-guided synthetic multimodal data generation, 2025c. URL https://arxiv.org/abs/2502.14846 . ↗
  128. Z. Yang, J. Tang, Z. Li, P. Wang, J. Wan, H. Zhong, X. Liu, M. Yang, P. Wang, S. Bai, L. Jin, and J. Lin. Cc-ocr: A comprehensive and challenging ocr benchmark for evaluating large multimodal models in literacy, 2024. URL https://arxiv.org/abs/2412.02210 . — [arXiv:2412.02210](https://arxiv.org/abs/2412.02210) ↗
  129. C. Yao, X. Bai, W. Liu, Y. Ma, and Z. Tu. Detecting texts of arbitrary orientations in natural images. 2012. URL https://pages.ucsd.edu/~ztu/publication/cvpr12_textdete ction.pdf . ↗
  130. F. Yao, L. Liu, D. Zhang, C. Dong, J. Shang, and J. Gao. Your efficient rl framework secretly brings you off-policy rl training, Aug. 2025. URL https://fengyao.notion.site/off-p olicy-rl . ↗
  131. C.-H. Yeh, C. Wang, S. Tong, T.-Y. Cheng, R. Wang, T. Chu, Y. Zhai, Y. Chen, S. Gao, and Y. Ma. Seeing from another perspective: Evaluating multi-view understanding in mllms, 2025. URL https://arxiv.org/abs/2504.15280 . — [arXiv:2504.15280](https://arxiv.org/abs/2504.15280) ↗
  132. B. Yin, Q. Wang, P. Zhang, J. Zhang, K. Wang, Z. Wang, J. Zhang, K. Chandrasegaran, H. Liu, R. Krishna, S. Xie, M. Li, J. Wu, and L. Fei-Fei. Spatial mental modeling from limited views, 2025. URL https://arxiv.org/abs/2506.21458 . ↗
  133. K. Ying, F. Meng, J. Wang, Z. Li, H. Lin, Y. Yang, H. Zhang, W. Zhang, Y. Lin, S. Liu, J. Lei, Q. Lu, R. Chen, P. Xu, R. Zhang, H. Zhang, P. Gao, Y. Wang, Y. Qiao, P. Luo, K. Zhang, and W. Shao. Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multi… — [arXiv:2404.16006](https://arxiv.org/abs/2404.16006) find
  134. E. Yu, L. Zhao, Y. Wei, J. Yang, D. Wu, L. Kong, H. Wei, T. Wang, Z. Ge, X. Zhang, et al. Merlin: Empowering multimodal llms with foresight minds. In European Conference on Computer Vision, pages 425–443. Springer, 2024. find
  135. E. Yu, K. Lin, L. Zhao, Y. Wei, Z. Zhu, H. Wei, J. Sun, Z. Ge, X. Zhang, J. Wang, et al. Unhackable temporal rewarding for scalable video mllms. arXiv preprint arXiv:2502.12081, 2025a. — [arXiv:2502.12081](https://arxiv.org/abs/2502.12081) find
  136. E. Yu, K. Lin, L. Zhao, J. Yin, Y. Wei, Y. Peng, H. Wei, J. Sun, C. Han, Z. Ge, et al. Perception-r1: Pioneering perception policy with reinforcement learning. arXiv preprint arXiv:2504.07954, 2025b. — [arXiv:2504.07954](https://arxiv.org/abs/2504.07954) find
  137. Y. Yuan, X. Liu, W. Dikubab, H. Liu, Z. Ji, Z. Wu, and X. Bai. Syntax-aware network for handwritten mathematical expression recognition. arXiv preprint arXiv:2203.01601, 2022. — [arXiv:2203.01601](https://arxiv.org/abs/2203.01601) find
  138. X. Yue, Y. Ni, K. Zhang, T. Zheng, R. Liu, G. Zhang, S. Stevens, D. Jiang, W. Ren, Y. Sun, et al. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9556–9567, 2…
  139. Y. Yue, Z. Chen, R. Lu, A. Zhao, Z. Wang, S. Song, and G. Huang. Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? arXiv preprint arXiv:2504.13837, 2025.
  140. R. Zellers, Y. Bisk, A. Farhadi, and Y. Choi. From recognition to cognition: Visual commonsense reasoning, 2019. URL https://arxiv.org/abs/1811.10830 . ↗
  141. F. Zhang, L. Wu, H. Bai, G. Lin, X. Li, X. Yu, Y. Wang, B. Chen, and J. Keung. Humaneval-v: Benchmarking high-level visual reasoning with complex diagrams in coding tasks, 2025. URL https://arxiv.org/abs/2410.12381 . — [arXiv:2410.12381](https://arxiv.org/abs/2410.12381) ↗
  142. R. Zhang, D. Jiang, Y. Zhang, H. Lin, Z. Guo, P. Qiu, A. Zhou, P. Lu, K.-W. Chang, P. Gao, and H. Li. Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?, 2024. URL https://arxiv.org/abs/2403.14624 . ↗
  143. J. Zhou, T. Lu, S. Mishra, S. Brahma, S. Basu, Y. Luan, D. Zhou, and L. Hou. Instruction-following evaluation for large language models, 2023. URL https://arxiv.org/abs/2311.07911 . ↗
  144. C. Zou, X. Guo, R. Yang, J. Zhang, B. Hu, and H. Zhang. Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models, 2024. 7. Author List All authors are listed in alphabetical order by their first names. † indicates project leaders. find
  145. Core Contributors Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun † , Jingcheng Hu, Kangheng Lin, Liang Zhao † , Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/huang-2026-step3-vl-10b-technical/