Elamur Research
☰
home / papers / 2025 / InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Written for the Research library (claude-opus-5-5) from the paper text. Original — arxiv.org/pdf/2504.10479

Summary

Most strong multimodal LLMs begin as text-only LLMs and gain vision later through multi-stage pipelines. This approach makes modality alignment difficult and often requires freezing parameters or adding specialized data to preserve language skills. InternVL3 replaces this with native multimodal pre-training: a single stage that mixes image–text, video–text and interleaved data with large text corpora. The model learns language and vision together from the start. It keeps the "ViT-MLP-LLM" design, with InternViT encoders and base (not instruction-tuned) Qwen2.5 or InternLM3 LLMs. It adds Variable Visual Position Encoding (V2PE), which uses fractional position steps for visual tokens so longer multimodal contexts fit. Post-training uses SFT and mixed preference optimization (MPO), and inference uses test-time scaling. The flagship InternVL3-78B scores 72.2 on MMMU, the best open-source result reported. It stays close to proprietary systems such as Gemini-2.5 Pro and keeps solid text-only ability. The authors promise to release both weights and training data, which supports reproducible open MLLM research.

Key points

  • Seven models range from 0.9B to 78.4B parameters. They combine InternViT-300M-448px-V2.5 or InternViT-6B-448px-V2.5 with Qwen2.5 (0.5B–72B) or InternLM3-8B. InternVL3-78B scores 79.5 on the OpenCompass academic leaderboard.
  • Pixel unshuffle compresses each 448×448 image tile to 256 visual tokens.
  • In V2PE, text tokens advance the position index by 1 and visual tokens by δ < 1. During training, δ is sampled per image from {1, 1/2, …, 1/256}. Ablations show that small δ helps even on short-context tasks.
  • In an ablation on InternVL2-8B, replacing the MLP warmup with native pre-training alone matched the fully multi-stage baseline on most benchmarks.
  • MPO lifts the average across seven reasoning benchmarks by 4.1 points for the 78B model and 4.5 points for the 38B model, using only a subset of the SFT data. Code, weights and InternVL-Data are hosted by OpenGVLab on GitHub and Hugging Face.

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: Natural language processing

Cited by

186 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 185 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2504.10479 · arXiv 2504.10479

@misc{zhu2025internvl3,
  title = {{InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models}},
  author = {Zhu, Jinguo and Wang, Weiyun and Chen, Zhe and Liu, Zhaoyang and Ye, Shenglong and Gu, Lixin and Tian, Hao and Duan, Yuchen and Su, Weijie and Shao, Jie and Gao, Zhangwei and Cui, Erfei and Wang, Xuehui and Cao, Yue and Liu, Yangzhou and Wei, Xingguang and Zhang, Hongjie and Wang, Haomin and Xu, Weiye and Li, Hao and Wang, Jiahao and Deng, Nianchen and Li, Songze and He, Yinan and Jiang, Tan and Luo, Jiapeng and Wang, Yi and He, Conghui and Shi, Botian and Zhang, Xingcheng and Shao, Wenqi and He, Junjun and Xiong, Yingtong and Qu, Wenwen and Sun, Peng and Jiao, Penglong and Lv, Han and Wu, Lijun and Zhang, Kaipeng and Deng, Huipeng and Ge, Jiaye and Chen, Kai and Wang, Limin and Dou, Min and Lu, Lewei and Zhu, Xizhou and Lu, Tong and Lin, Dahua and Qiao, Yu and Dai, Jifeng and Wang, Wenhai},
  year = {2025},
  doi = {10.48550/arxiv.2504.10479},
  eprint = {2504.10479},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.10479}
}

References

155 references, 64 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023. 15 find our card
  2. Anonymous. CG-bench: Clue-grounded question answering benchmark for long video understanding. In Submitted to The Thirteenth International Conference on Learning Representations, 2024. under review. 14, 15 find
  3. Anthropic. The claude 3 model family: Opus, sonnet, haiku. https://www.anthropic.com, 2024. 2, 8, 9, 10, 11, 12 ↗
  4. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. Program synthesis with large language models. arXiv preprint arXiv:2108.07732, 2021. 16 find our card
  5. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966, 2023. 1, 2 find our card
  6. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, et al. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923, 2025. 11, 12, 13, 14 find our card
  7. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, et al. Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923, 2025. 1, 2, 9, 10, 15 find our card
  8. Loubna Ben Allal, Anton Lozhkov, Guilherme Penedo, Thomas Wolf, and Leandro von Werra. Smollm-corpus, 2024. 5 find
  9. Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marçal Rusinol, Ernest Valveny, CV Jawahar, and Dimosthenis Karatzas. Scene text visual question answering. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4291–4301, 2019. 6 find
  10. Jie Cao and Jing Xiao. An augmented benchmark dataset for geometric question answering through dual parallel text encoding. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1511–1520, 2022. 6 find
  11. Shuaichen Chang, David Palzer, Jialin Li, Eric Fosler-Lussier, and Ningchuan Xiao. Mapqa: A dataset for question answering on choropleth maps. arXiv preprint arXiv:2211.08545, 2022. 6 — [arXiv:2211.08545](https://arxiv.org/abs/2211.08545) find
  12. Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195, 2023. 13 find our card
  13. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, et al. Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330, 2024. 12 find our card
  14. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, 2021. 16 find our card
  15. Qiaoling Chen, Diandian Gu, Guoteng Wang, Xun Chen, YingTong Xiong, Ting Huang, Qinghao Hu, Xin Jin, Yonggang Wen, Tianwei Zhang, et al. Internevo: Efficient long-sequence large language model training via hybrid parallelism and redundant sharding. arXiv preprint arXiv:2401.09149, 2024. 2, 7 find
  16. Qiguang Chen, Libo Qin, Jin Zhang, Zhi Chen, Xiao Xu, and Wanxiang Che. M3cot: A novel benchmark for multi-domain multi-step multi-modal chain-of-thought. arXiv preprint arXiv:2405.16473, 2024. 6 — [arXiv:2405.16473](https://arxiv.org/abs/2405.16473) find
  17. Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, and Tony Xia. Theoremqa: A theorem-driven question answering dataset. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EM… find our card
  18. 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. arXiv preprint arXiv:2412.05271, 2024. 1, 2, 3, 5, 6, 9, 10, 11,… find our card
  19. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, et al. How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821, 2024. 1, 3, 10, 11, 12, 13, 14, 15 find our card
  20. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, et al. How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821, 2024. 2, 3 find our card
  21. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 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 Recogni… find our card
  22. Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, and Zhiyong Wu. Seeclick: Harnessing gui grounding for advanced visual gui agents. arXiv preprint arXiv:2401.10935, 2024. 16 find our card
  23. Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, et al. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476, 2024. 15 find
  24. Christopher Clark and Matt Gardner. Simple and effective multi-paragraph reading comprehension. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 845–855, 2018. 6 find our card
  25. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021. 16 find our card
  26. OpenCompass Contributors. Opencompass: A universal evaluation platform for foundation models. https: //github.com/open-compass/opencompass, 2023. 9, 10, 11, 12 find
  27. X.AI Corp. Grok-1.5 vision preview: Connecting the digital and physical worlds with our first multimodal model. https://x.ai/blog/grok-1.5v, 2024. 11 ↗
  28. Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuolin Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. Nvlm: Open frontier-class multimodal llms. arXiv preprint arXiv:2409.11402, 2024. 10 find
  29. Google Deepmind. Gemini 2.0 is now available to everyone. https://blog.google/technology/ google-deepmind/gemini-model-updates-february-2025/, 202. 9 ↗
  30. Google Deepmind. Introducing gemini 2.0: our new ai model for the agentic era. https://blog.google/ technology/google-deepmind/google-gemini-ai-update-december-2024/, 2024. 9 ↗
  31. Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al. Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models. arXiv preprint arXiv:2409.17146, 2024. 1, 10 find our card
  32. Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Bin Wang, Linke Ouyang, Songyang Zhang, Haodong Duan, Wenwei Zhang, Yining Li, et al. Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd. arXiv preprint arXiv:2404.06512, 2024. 1 find
  33. 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, pages 11198–11201, 20… find
  34. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024. 10 find
  35. Xinyu Fang, Kangrui Mao, Haodong Duan, Xiangyu Zhao, Yining Li, Dahua Lin, and Kai Chen. Mmbench-video: A long-form multi-shot benchmark for holistic video understanding. arXiv preprint arXiv:2406.14515, 2024. 14, 15 — [arXiv:2406.14515](https://arxiv.org/abs/2406.14515) find
  36. Li Fei-Fei, Rob Fergus, and Pietro Perona. Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In Conference on Computer Vision and Pattern Recognition Workshop, pages 178–178, 2004. 7 find
  37. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Zhenyu Qiu, Wei Lin, Jinrui Yang, Xiawu Zheng, et al. Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394, 2023. 12 find our card
  38. Chaoyou Fu, Yuhan Dai, Yondong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, et al. Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis. arXiv preprint arXiv:2405.21075, 2024. 14, 15 find our card
  39. Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A Smith, Wei-Chiu Ma, and Ranjay Krishna. Blink: Multimodal large language models can see but not perceive. arXiv preprint arXiv:2404.12390, 2024. 9, 11 find
  40. Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing Hong, Jianhua Han, Hang Xu, Zhenguo Li, et al. G-llava: Solving geometric problem with multi-modal large language model. arXiv preprint arXiv:2312.11370, 2023. 6 find
  41. Zhangwei Gao, Zhe Chen, Erfei Cui, Yiming Ren, Weiyun Wang, Jinguo Zhu, Hao Tian, Shenglong Ye, Junjun He, Xizhou Zhu, et al. Mini-internvl: A flexible-transfer pocket multimodal model with 5% parameters and 90% performance. arXiv preprint arXiv:2410.16261, 2024. 3 find
  42. Junqi Ge, Ziyi Chen, Jintao Lin, Jinguo Zhu, Xihui Liu, Jifeng Dai, and Xizhou Zhu. V2pe: Improving multimodal long-context capability of vision-language models with variable visual position encoding. arXiv preprint arXiv:2412.09616, 2024. 2, 3, 18 — [arXiv:2412.09616](https://arxiv.org/abs/2412.09616) find
  43. Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6904–6913, 2017. 6 find our card
  44. Shuhao Gu, Jialing Zhang, Siyuan Zhou, Kevin Yu, Zhaohu Xing, Liangdong Wang, Zhou Cao, Jintao Jia, Zhuoyi Zhang, Yixuan Wang, et al. Infinity-mm: Scaling multimodal performance with large-scale and high-quality instruction data. arXiv preprint arXiv:2410.18558, 2024. 9, 10 find
  45. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, et al. Hallusionbench: An advanced diagnostic suite for entangled language hallucination & visual illusion in large vision-language models. arXiv preprint arXiv:2310.14566,… find our card
  46. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. In The International Conference on Learning Representations, 2020. 16 find our card
  47. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathematical problem solving with the MATH dataset. In Joaquin Vanschoren and Sai-Kit Yeung, editors, Proceedings of the Neural Information Processing Systems Track on Datas… find our card
  48. Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Yao Fu, et al. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems, 36, 2024. 16 find our card
  49. Zheng Huang, Kai Chen, Jianhua He, Xiang Bai, Dimosthenis Karatzas, Shijian Lu, and CV Jawahar. Icdar2019 competition on scanned receipt ocr and information extraction. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 1516–1520. IEEE, 2019. 6 find
  50. Drew A Hudson and Christopher D Manning. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6700–6709, 2019. 6 find our card
  51. Dongfu Jiang, Xuan He, Huaye Zeng, Cong Wei, Max Ku, Qian Liu, and Wenhu Chen. Mantis: Interleaved multi-image instruction tuning. arXiv preprint arXiv:2405.01483, 2024. 9, 11 find
  52. Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551, 2017. 16 find our card
  53. Seungjae Jung, Gunsoo Han, Daniel Wontae Nam, and Kyoung-Woon On. Binary classifier optimization for large language model alignment. arXiv preprint arXiv:2404.04656, 2024. 6 find
  54. Kushal Kafle, Brian Price, Scott Cohen, and Christopher Kanan. Dvqa: Understanding data visualizations via question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5648–5656, 2018. 6 find
  55. Mehran Kazemi, Hamidreza Alvari, Ankit Anand, Jialin Wu, Xi Chen, and Radu Soricut. Geomverse: A systematic evaluation of large models for geometric reasoning. arXiv preprint arXiv:2312.12241, 2023. 6 — [arXiv:2312.12241](https://arxiv.org/abs/2312.12241) find
  56. Sahar Kazemzadeh, Vicente Ordonez, Mark Matten, and Tamara Berg. Referitgame: Referring to objects in photographs of natural scenes. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 787–798, 2014. 13 find
  57. Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, and Ali Farhadi. A diagram is worth a dozen images. In European Conference on Computer Vision, pages 235–251, 2016. 6, 7, 8, 10 find our card
  58. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics, 7:4… find our card
  59. Guokun Lai, Qizhe Xie, Hanxiao Liu, Yiming Yang, and Eduard Hovy. Race: Large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683, 2017. 16 find our card
  60. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326, 2024. 9, 10, 11, 12, 15, 16 find our card
  61. Bohao Li, Yuying Ge, Yi Chen, Yixiao Ge, Ruimao Zhang, and Ying Shan. Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension. arXiv preprint arXiv:2404.16790, 2024. 8, 10 — [arXiv:2404.16790](https://arxiv.org/abs/2404.16790) find
  62. Chunyi Li, Jianbo Zhang, Zicheng Zhang, Haoning Wu, Yuan Tian, Wei Sun, Guo Lu, Xiaohong Liu, Xiongkuo Min, Weisi Lin, et al. R-bench: Are your large multimodal model robust to real-world corruptions? arXiv preprint arXiv:2410.05474, 2024. 11 — [arXiv:2410.05474](https://arxiv.org/abs/2410.05474) find
  63. Haonan Li, Yixuan Zhang, Fajri Koto, Yifei Yang, Hai Zhao, Yeyun Gong, Nan Duan, and Timothy Baldwin. Cmmlu: Measuring massive multitask language understanding in chinese. arXiv preprint arXiv:2306.09212, 2023. 16 find our card
  64. KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355, 2023. 15 find our card
  65. Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, et al. Mvbench: A comprehensive multi-modal video understanding benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22195–22206, 2024. 14, 15 find our card
  66. Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, and Christoph Feichtenhofer. Mvitv2: Improved multiscale vision transformers for classification and detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4804–4814, 20… find
  67. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. Evaluating object hallucination in large vision-language models. In The Conference on Empirical Methods in Natural Language Processing, pages 292–305, 2023. 12, 13 find our card
  68. Zhang Li, Biao Yang, Qiang Liu, Zhiyin Ma, Shuo Zhang, Jingxu Yang, Yabo Sun, Yuliang Liu, and Xiang Bai. Monkey: Image resolution and text label are important things for large multi-modal models. arXiv preprint arXiv:2311.06607, 2023. 1 find
  69. Zhiqi Li, Guo Chen, Shilong Liu, Shihao Wang, Vibashan VS, Yishen Ji, Shiyi Lan, Hao Zhang, Yilin Zhao, Subhashree Radhakrishnan, et al. Eagle 2: Building post-training data strategies from scratch for frontier vision-language models. arXiv preprint arXiv:2501.14818, 2025. 1 — [arXiv:2501.14818](https://arxiv.org/abs/2501.14818) find
  70. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, 2023. 7 find our card
  71. Ji Lin, Hongxu Yin, Wei Ping, Pavlo Molchanov, Mohammad Shoeybi, and Song Han. Vila: On pre-training for visual language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26689–26699, 2024. 1, 9, 10, 15, 16 find our card
  72. Adam Dahlgren Lindström and Savitha Sam Abraham. Clevr-math: A dataset for compositional language, visual and mathematical reasoning. arXiv preprint arXiv:2208.05358, 2022. 6 — [arXiv:2208.05358](https://arxiv.org/abs/2208.05358) find
  73. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. Advances in Neural Information Processing Systems, 36, 2023. 2 find our card
  74. Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European Conference on Computer Vision, pages 38–55. Springer, 2025. 13 find our card
  75. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, et al. Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281, 2023. 12 find our card
  76. Yuliang Liu, Zhang Li, Hongliang Li, Wenwen Yu, Mingxin Huang, Dezhi Peng, Mingyu Liu, Mingrui Chen, Chunyuan Li, Lianwen Jin, et al. On the hidden mystery of ocr in large multimodal models. arXiv preprint arXiv:2305.07895, 2023. 8, 10 find our card
  77. Zihan Liu, Yang Chen, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. Acemath: Advancing frontier math reasoning with post-training and reward modeling. arXiv preprint, 2024. 5 find
  78. Zuyan Liu, Yuhao Dong, Ziwei Liu, Winston Hu, Jiwen Lu, and Yongming Rao. Oryx mllm: On-demand spatial-temporal understanding at arbitrary resolution. arXiv preprint arXiv:2409.12961, 2024. 15 — [arXiv:2409.12961](https://arxiv.org/abs/2409.12961) find
  79. Dakuan Lu, Xiaoyu Tan, Rui Xu, Tianchu Yao, Chao Qu, Wei Chu, Yinghui Xu, and Yuan Qi. Scp-116k: A high-quality problem-solution dataset and a generalized pipeline for automated extraction in the higher education science domain, 2025. 5 find
  80. 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. arXiv preprint arXiv:2310.02255, 2023. 7, 8, 9 find our card
  81. 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. arXiv preprint arXiv:2105.04165, 2021. 6 find our card
  82. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35:2507–2521, 2022. 6 find
  83. Pan Lu, Liang Qiu, Jiaqi Chen, Tony Xia, Yizhou Zhao, Wei Zhang, Zhou Yu, Xiaodan Liang, and Song-Chun Zhu. Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning. arXiv preprint arXiv:2110.13214, 2021. 6 find
  84. Shiyin Lu, Yang Li, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, and Han-Jia Ye. Ovis: Structural embedding alignment for multimodal large language model. arXiv preprint arXiv:2405.20797, 2024. 9, 10 — [arXiv:2405.20797](https://arxiv.org/abs/2405.20797) find
  85. Xudong Lu, Yinghao Chen, Cheng Chen, Hui Tan, Boheng Chen, Yina Xie, Rui Hu, Guanxin Tan, Renshou Wu, Yan Hu, et al. Bluelm-v-3b: Algorithm and system co-design for multimodal large language models on mobile devices. arXiv preprint arXiv:2411.10640, 2024. 1 — [arXiv:2411.10640](https://arxiv.org/abs/2411.10640) find
  86. Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, and Bill Yuchen Lin. Wildvision: Evaluating vision-language models in the wild with human preferences. arXiv preprint arXiv:2406.11069, 2024. 11 — [arXiv:2406.11069](https://arxiv.org/abs/2406.11069) find
  87. Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, et al. Improve mathematical reasoning in language models by automated process supervision. arXiv preprint arXiv:2406.06592, 2, 2024. 7 find our card
  88. Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan L Yuille, and Kevin Murphy. Generation and comprehension of unambiguous object descriptions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11–20, 2016. 13 find our card
  89. Andrés Marafioti, Orr Zohar, Miquel Farré, Merve Noyan, Elie Bakouch, Pedro Cuenca, Cyril Zakka, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, et al. Smolvlm: Redefining small and efficient multimodal models. arXiv preprint arXiv:2504.05299, 2025. 1 find
  90. Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. Ok-vqa: A visual question answering benchmark requiring external knowledge. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3195–3204, 2019. 6 find
  91. Ahmed Masry, Xuan Long Do, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. Chartqa: A benchmark for question answering about charts with visual and logical reasoning. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 2263–2279, 2022. 6, 7, 8, 10 find our card
  92. Minesh Mathew, Viraj Bagal, Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. Infographicvqa. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1697–1706, 2022. 6, 7, 8, 10 find
  93. Minesh Mathew, Dimosthenis Karatzas, and CV Jawahar. Docvqa: A dataset for vqa on document images. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2200–2209, 2021. 7, 8, 10 find our card
  94. Nat McAleese, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, and Jan Leike. Llm critics help catch llm bugs. arXiv preprint arXiv:2407.00215, 2024. 7 — [arXiv:2407.00215](https://arxiv.org/abs/2407.00215) find
  95. Fanqing Meng, Jin Wang, Chuanhao Li, Quanfeng Lu, Hao Tian, Jiaqi Liao, Xizhou Zhu, Jifeng Dai, Yu Qiao, Ping Luo, et al. Mmiu: Multimodal multi-image understanding for evaluating large vision-language models. arXiv preprint arXiv:2408.02718, 2024. 9, 11 — [arXiv:2408.02718](https://arxiv.org/abs/2408.02718) find
  96. Anand Mishra, Shashank Shekhar, Ajeet Kumar Singh, and Anirban Chakraborty. Ocr-vqa: Visual question answering by reading text in images. In International Conference on Document Analysis and Recognition, pages 947–952, 2019. 6 find
  97. OpenAI. Gpt-4v(ision) system card. https://cdn.openai.com/papers/GPTV\_System\_Card.pdf, 2023. 1, 8, 9, 10, 11, 12, 14, 15, 16 ↗
  98. OpenAI. Gpt-4o system card. https://openai.com/index/gpt-4o-system-card/, 2025. 2, 8 ↗ our card
  99. Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, et al. We-math: Does your large multimodal model achieve human-like mathematical reasoning? arXiv preprint arXiv:2407.01284, 2024. 8, 9 find
  100. Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, et al. Ui-tars: Pioneering automated gui interaction with native agents. arXiv preprint arXiv:2501.12326, 2025. 16 find our card
  101. 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. Advances in Neural Information Processing Systems, 36, 2024. 6 find
  102. Machel Reid, Nikolay Savinov, Denis Teplyashin, Dmitry Lepikhin, Timothy Lillicrap, Jean-baptiste Alayrac, Radu Soricut, Angeliki Lazaridou, Orhan Firat, Julian Schrittwieser, et al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530,… find our card
  103. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 8732–8740, 2020. 16 find
  104. Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni, and Clint Malcolm. Solving geometry problems: Combining text and diagram interpretation. In Proceedings of the 2015 conference on empirical methods in natural language processing, pages 1466–1476, 2015. 6 find
  105. Min Shi, Fuxiao Liu, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, et al. Eagle: Exploring the design space for multimodal llms with mixture of encoders. arXiv preprint arXiv:2408.15998, 2024. 1 — [arXiv:2408.15998](https://arxiv.org/abs/2408.15998) find
  106. Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, and Roy Ka-Wei Lee. Math-llava: Bootstrapping mathematical reasoning for multimodal large language models. arXiv preprint arXiv:2406.17294, 2024. 6 find
  107. Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. Towards vqa models that can read. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8317–8326, 2019. 6, 8, 10 find
  108. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314, 2024. 7 find our card
  109. Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, et al. Parrot: Multilingual visual instruction tuning. arXiv preprint arXiv:2406.02539, 2024. 14 — [arXiv:2406.02539](https://arxiv.org/abs/2406.02539) find
  110. Kai Sun, Dian Yu, Dong Yu, and Claire Cardie. Investigating prior knowledge for challenging chinese machine reading comprehension. Transactions of the Association for Computational Linguistics, 8:141–155, 2020. 16 find
  111. Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liang-Yan Gui, Yu-Xiong Wang, Yiming Yang, et al. Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:2309.14525, 2023. 12, 13 find our card
  112. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, et al. Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261, 2022. 16 find our card
  113. Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, Chunhui Lin, Wanqing Li, Mohamad Fitri Faiz Bin Mahmood, Hao Feng, Zhen Zhao, et al. Mtvqa: Benchmarking multilingual text-centric visual question answering. arXiv preprint arXiv:2405.11985, 2024. 14 find
  114. Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023. 1, 14 find our card
  115. Qwen Team. Qvq: To see the world with wisdom, December 2024. 9 find
  116. Shengbang Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, et al. Cambrian-1: A fully open, vision-centric exploration of multimodal llms. arXiv preprint arXiv:2406.16860, 2024. 9, 10, 11, 12 find our card
  117. v DeepMind. Gemini 2.5 pro. https://deepmind.google/technologies/gemini/pro/, 2025. 1, 2, 8 ↗
  118. Fei Wang, Xingyu Fu, James Y Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, et al. Muirbench: A comprehensive benchmark for robust multi-image understanding. arXiv preprint arXiv:2406.09411, 2024. 9, 11 — [arXiv:2406.09411](https://arxiv.org/abs/2406.09411) find
  119. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Mingjie Zhan, and Hongsheng Li. Measuring multimodal mathematical reasoning with math-vision dataset. arXiv preprint arXiv:2402.14804, 2024. 8, 9 find our card
  120. Peiyi Wang, Lei Li, Zhihong Shao, RX Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. arXiv preprint arXiv:2312.08935, 2023. 7 find our card
  121. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.12191, 2024. 1, 8, 10, 11, 12, 13, 14, 15 find our card
  122. Peng Wang, Shijie Wang, Junyang Lin, Shuai Bai, Xiaohuan Zhou, Jingren Zhou, Xinggang Wang, and Chang Zhou. One-peace: Exploring one general representation model toward unlimited modalities. arXiv:2305.11172, 2023. 13 — [arXiv:2305.11172](https://arxiv.org/abs/2305.11172) find
  123. Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Xixuan Song, et al. Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079, 2023. 1, 13 find our card
  124. 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. arXiv preprint arXiv:2411.10442, 2024. 2, 6, 7 find
  125. Weiyun Wang, Zhangwei Gao, Lianjie Chen, Zhe Chen, Jinguo Zhu, Xiangyu Zhao, Yangzhou Liu, Yue Cao, Shenglong Ye, Xizhou Zhu, et al. Visualprm: An effective process reward model for multimodal reasoning. arXiv preprint arXiv:2503.10291, 2025. 2, 7, 8, 9 — [arXiv:2503.10291](https://arxiv.org/abs/2503.10291) find
  126. Weiyun Wang, Yiming Ren, Haowen Luo, Tiantong Li, Chenxiang Yan, Zhe Chen, Wenhai Wang, Qingyun Li, Lewei Lu, Xizhou Zhu, et al. The all-seeing project v2: Towards general relation comprehension of the open world. arXiv preprint arXiv:2402.19474, 2024. 6, 12, 13 — [arXiv:2402.19474](https://arxiv.org/abs/2402.19474) find
  127. Weiyun Wang, Min Shi, Qingyun Li, Wenhai Wang, Zhenhang Huang, Linjie Xing, Zhe Chen, Hao Li, Xizhou Zhu, Zhiguo Cao, et al. The all-seeing project: Towards panoptic visual recognition and understanding of the open world. In The International Conference on Learning Representations, 2024. 6 find
  128. Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, et al. Charxiv: Charting gaps in realistic chart understanding in multimodal llms. arXiv preprint arXiv:2406.18521, 2024. 8, 10 find
  129. Haoning Wu, Dongxu Li, Bei Chen, and Junnan Li. Longvideobench: A benchmark for long-context interleaved video-language understanding. arXiv preprint arXiv:2407.15754, 2024. 8, 14, 15 find
  130. Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, et al. Os-atlas: A foundation action model for generalist gui agents. arXiv preprint arXiv:2410.23218, 2024. 16 find
  131. Yijia Xiao, Edward Sun, Tianyu Liu, and Wei Wang. Logicvista: Multimodal llm logical reasoning benchmark in visual contexts. arXiv preprint arXiv:2407.04973, 2024. 8, 9 — [arXiv:2407.04973](https://arxiv.org/abs/2407.04973) find
  132. Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu, and Caiming Xiong. Aguvis: Unified pure vision agents for autonomous gui interaction. 2024. 16 find
  133. B. Yan, Yi Jiang, Jiannan Wu, D. Wang, Ping Luo, Zehuan Yuan, and Huchuan Lu. Universal instance perception as object discovery and retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. 13 find
  134. Jihan Yang, Shusheng Yang, Anjali Gupta, Rilyn Han, Li Fei-Fei, and Saining Xie. Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces. arXiv preprint arXiv:2412.14171, 2024. 16 find
  135. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800, 2024. 9, 10, 11, 12, 15 find our card
  136. Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Haowei Liu, Qi Qian, Ji Zhang, Fei Huang, and Jingren Zhou. mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. arXiv preprint arXiv:2311.04257, 2023. 1, 14 find our card
  137. Kaining Ying, Fanqing Meng, Jin Wang, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, Jiayi Lei, Quanfeng Lu, Runjian Chen, Peng Xu, Renrui Zhang, Haozhe Zhang, Peng Gao, Yali Wang, Yu Qiao, Ping Luo, Kaipeng Zhang, and Wenqi Shao. Mmt-bench: A comprehensive multimodal ben… — [arXiv:2404.16006](https://arxiv.org/abs/2404.16006) find
  138. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490, 2023. 12 find our card
  139. Weihao Yu, Zhengyuan Yang, Linfeng Ren, Linjie Li, Jianfeng Wang, Kevin Lin, Chung-Ching Lin, Zicheng Liu, Lijuan Wang, and Xinchao Wang. Mm-vet v2: A challenging benchmark to evaluate large multimodal models for integrated capabilities. arXiv preprint arXiv:2408.00765, 2024. 12 — [arXiv:2408.00765](https://arxiv.org/abs/2408.00765) find
  140. Ya-Qi Yu, Minghui Liao, Jiwen Zhang, and Jihao Wu. Texthawk2: A large vision-language model excels in bilingual ocr and grounding with 16x fewer tokens. arXiv preprint arXiv:2410.05261, 2024. 13 — [arXiv:2410.05261](https://arxiv.org/abs/2410.05261) find
  141. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, et al. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. arXiv preprint arXiv:2311.16502, 2023. 2, 7, 8, 9 find our card
  142. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. Hellaswag: Can a machine really finish your sentence? In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 4791–4800, 2019. 16 find
  143. Haotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, et al. Mm1.5: Methods, analysis & insights from multimodal llm fine-tuning. arXiv preprint arXiv:2409.20566, 2024. 13 — [arXiv:2409.20566](https://arxiv.org/abs/2409.20566) find
  144. Haotian Zhang, Haoxuan You, Philipp Dufter, Bowen Zhang, Chen Chen, Hong-You Chen, Tsu-Jui Fu, William Yang Wang, Shih-Fu Chang, Zhe Gan, et al. Ferret-v2: An improved baseline for referring and grounding with large language models. arXiv preprint arXiv:2404.07973, 2024. 13 — [arXiv:2404.07973](https://arxiv.org/abs/2404.07973) find
  145. Peiyuan Zhang, Kaichen Zhang, Bo Li, Guangtao Zeng, Jingkang Yang, Yuanhan Zhang, Ziyue Wang, Haoran Tan, Chunyuan Li, and Ziwei Liu. Long context transfer from language to vision. arXiv preprint arXiv:2406.16852, 2024. 16 find
  146. Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Peng Gao, et al. Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? arXiv preprint arXiv:2403.14624, 2024. 8, 9 find our card
  147. Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Yichi Zhang, Ziyu Guo, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, et al. Mavis: Mathematical visual instruction tuning. arXiv preprint arXiv:2407.08739, 2024. 6 — [arXiv:2407.08739](https://arxiv.org/abs/2407.08739) find
  148. Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, and Yoshua Bengio. Vcr: Visual caption restoration. arXiv preprint arXiv:2406.06462, 2024. 8, 10 — [arXiv:2406.06462](https://arxiv.org/abs/2406.06462) find
  149. Xiaotian Zhang, Chunyang Li, Yi Zong, Zhengyu Ying, Liang He, and Xipeng Qiu. Evaluating the performance of large language models on gaokao benchmark. arXiv preprint arXiv:2305.12474, 2023. 16 find
  150. Y Zhang, B Li, H Liu, Y Lee, L Gui, D Fu, J Feng, Z Liu, and C Li. Llava-next: A strong zero-shot video understanding model. 2024. 16 find
  151. Yi-Fan Zhang, Huanyu Zhang, Haochen Tian, Chaoyou Fu, Shuangqing Zhang, Junfei Wu, Feng Li, Kun Wang, Qingsong Wen, Zhang Zhang, et al. Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenarios that are difficult for humans? arXiv preprint arXiv:2408.13257, 2024. 11 — [arXiv:2408.13257](https://arxiv.org/abs/2408.13257) find
  152. Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. The lessons of developing process reward models in mathematical reasoning. arXiv preprint arXiv:2501.07301, 2025. 7 find our card
  153. Bingchen Zhao, Yongshuo Zong, Letian Zhang, and Timothy Hospedales. Benchmarking multi-image understanding in vision and language models: Perception, knowledge, reasoning, and multi-hop reasoning. arXiv preprint arXiv:2406.12742, 2024. 9, 11 — [arXiv:2406.12742](https://arxiv.org/abs/2406.12742) find
  154. Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Shitao Xiao, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, and Zheng Liu. Mlvu: A comprehensive benchmark for multi-task long video understanding. arXiv preprint arXiv:2406.04264, 2024. 14, 15 find
  155. Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, and Huan Zhang. Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models. arXiv preprint arXiv:2411.00836, 2024. 8, 9 find