Elamur Research⌕
☰
home / papers / 2025 / SmolVLM: Redefining small and efficient multimodal models

SmolVLM: Redefining small and efficient multimodal models

Paper · 2025 · Andres Marafioti, Orr Zohar, Miquel Farre et al.

Summary

Most compact vision-language models are shrunken copies of large ones. They inherit memory-hungry choices, such as producing many visual tokens per image, which makes them impractical on phones and edge hardware. The SmolVLM authors at Hugging Face and Stanford redesigned a small VLM from scratch. They paired SmolLM2 language backbones with SigLIP vision encoders and tested ablations over:

  • the encoder/LM size balance
  • context length
  • visual token compression
  • image splitting and video frame handling
  • positional tokenization of sub-images
  • instruction-data composition

The ablations favour a modest encoder, a longer context and stronger pixel-shuffle compression. They also favour learned positional tokens and dropping frame averaging for video. The resulting family spans 256M to 2.2B parameters. The smallest model runs in under 1GB of GPU memory and still outperforms Idefics-80B, a far larger model released about 18 months earlier. The 2.2B model competes with systems that need roughly twice the memory and handles video benchmarks such as Video-MME. All weights, datasets and code are open, which makes SmolVLM a practical base for low-cost, on-device multimodal applications.

Key points

  • Encoder/LM balance: SmolLM2 backbones (135M, 360M, 1.7B) were combined with SigLIP-B/16 (93M) or SigLIP-SO400M (428M).
    • With the 360M LM, the bigger encoder adds 11.6% performance but 66% more parameters, so the smaller encoder is the better trade-off at small scale.
  • Longer context: Raising the RoPE base from 10k to 273k extended the context to 16k tokens for the 2.2B model. The smaller variants are limited to 8k, since they were unstable beyond that.
  • Token compression and video: Small models gain from aggressive pixel shuffle (r = 4) compared with the r = 2 used by Idefics3 and InternVL.
    • Splitting images into sub-images helps.
    • Averaging video frames hurts OpenCompass-Video scores.
  • Sub-image position encoding: Learned positional tokens outperform string-based ones. The string variant caused an "OCR loss plague" in training for small models.
  • Efficiency and release: SmolVLM-256M needs under 1GB of GPU memory. Weights, data, code and the HuggingSnap mobile app are publicly released.

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

 Institutions

🎓Stanford UniversityStanford · United States567 works · 335,190 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksArtificial Intelligence · 18,805 worksComputer Vision and Pattern Recognition · 3,621 works

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 827 works

Cite

Cite as Andres Marafioti, Orr Zohar, Miquel Farre, Merve Noyan, Elie Bakouch, Pedro Cuenca, Cyril Zakka, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, Vaibhav Srivastav, Joshua Lochner, Hugo Larcher, Mathieu Morlon, Lewis Tunstall, Leandro von Werra and Thomas Wolf. 2025. SmolVLM: Redefining small and efficient multimodal models. arXiv:2504.05299.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2504.05299 · arXiv 2504.05299

@misc{marafioti2025smolvlm,
  title = {{SmolVLM: Redefining small and efficient multimodal models}},
  author = {Andres Marafioti, Orr Zohar, Miquel Farre, Merve Noyan, Elie Bakouch, Pedro Cuenca, Cyril Zakka, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, Vaibhav Srivastav, Joshua Lochner, Hugo Larcher, Mathieu Morlon, Lewis Tunstall, Leandro {von Werra} and Thomas Wolf},
  year = {2025},
  doi = {10.48550/arxiv.2504.05299},
  eprint = {2504.05299},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.05299}
}

References

98 references, 54 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.
  2. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob L Menick, Sebastian Borgeaud, Andy B… — Flamingo: a Visual Language Model for Few-Shot Learning
  3. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems, 35:23716–23736, 2022b.
  4. Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Martín Blázquez, Guilherme Penedo, Lewis Tunstall, Andrés Marafioti, Hynek Kydlíček, Agustín Piqueres Lajarín, Vaibhav Srivastav, Joshua Lochner, Caleb Fahlgren, Xuan-Son Nguyen, Clémentine Fourrier, Ben Burtenshaw, Hugo Larcher, Haojun Zhao, Cy… — SmolLM2: When Smol Goes Big — Data-Centric Training of a Small Language Model
  5. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision, pages 2425–2433, 2015. find
  6. Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R Manmatha. Docformer: End-to-end transformer for document understanding. In Proceedings of the IEEE/CVF international conference on computer vision, pages 993–1003, 2021. find
  7. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966, 2023.
  8. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Ha… — Qwen2.5-VL Technical Report
  9. Lucas Beyer, Andreas Steiner, André Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, et al. Paligemma: A versatile 3b vlm for transfer. arXiv preprint arXiv:2407.07726, 2024.
  10. Ali Furkan Biten, Rubèn Tito, Andrés Mafla, Lluis Gomez, Marçal Rusiñol, C.V. Jawahar, Ernest Valveny, and Dimosthenis Karatzas. Scene text visual question answering. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 4290–4300, 2019. doi: 10.1109/ICCV.2019.00439. find
  11. Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. Activitynet: A large-scale video benchmark for human activity understanding. In Proceedings of the ieee conference on computer vision and pattern recognition, pages 961–970, 2015. find
  12. David Chen and William B Dolan. Collecting highly parallel data for paraphrase evaluation. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pages 190–200, 2011.
  13. Lin Chen, Jisong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, and Dahua Lin. Sharegpt4v: Improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793, 2023.
  14. 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, 2024a.
  15. 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, 2024b.
  16. 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, 2024c.
  17. DeepSeek-AI. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025. https://arxiv.org/abs/2501.12948. ↗
  18. Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, Jiasen Lu, Taira Anderson, Erin Bransom, Kiana Ehsani, Huong Ngo, YenSung Chen, Ajay Patel, Mark Yatskar, Chris Callison-Burch, Andrew Head, Rose Hend… — Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
  19. 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. arXiv preprint arXiv:2407.11691, 2024. — [arXiv:2407.11691](https://arxiv.org/abs/2407.11691) find
  20. 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.
  21. Miquel Farré, Andi Marafioti, Lewis Tunstall, Leandro Von Werra, and Thomas Wolf. Finevideo. https://huggingface.co/datasets/HuggingFaceFV/finevideo, 2024. ↗
  22. Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. Colpali: Efficient document retrieval with vision language models. arXiv preprint arXiv:2407.01449, 2024a.
  23. Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. Colpali: Efficient document retrieval with vision language models, 2024b. https://arxiv.org/abs/2407.01449. ↗
  24. 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.
  25. Shaikat Galib, Shanshan Wang, Guanshuo Xu, Pascal Pfeiffer, Ryan Chesler, Mark Landry, and Sri Satish Ambati. H2ovl-mississippi vision language models technical report, 2024. https://arxiv.org/abs/2410.13611. ↗
  26. Philippe Gervais, Asya Fadeeva, and Andrii Maksai. Mathwriting: A dataset for handwritten mathematical expression recognition, 2024. https://arxiv.org/abs/2404.10690. — [arXiv:2404.10690](https://arxiv.org/abs/2404.10690) ↗
  27. 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 conference on computer vision and pattern recognition, pages 6904–6913, 2017.
  28. Jarvis Guo, Tuney Zheng, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Yizhi Li, Graham Neubig, Wenhu Chen, and Xiang Yue. Mammoth-vl: Eliciting multimodal reasoning with instruction tuning at scale. arXiv preprint arXiv:2412.05237, 2024.
  29. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556, 2022.
  30. Jack Hong, Shilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, and Weidi Xie. Worldsense: Evaluating real-world omnimodal understanding for multimodal llms, 2025. https://arxiv.org/abs/2502.04326. — [arXiv:2502.04326](https://arxiv.org/abs/2502.04326) ↗
  31. Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zheng Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, and Mao… — MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
  32. Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. Perceiver: General perception with iterative attention. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Lea…
  33. Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, and Ali Farhadi. A diagram is worth a dozen images. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling, editors, Computer Vision – ECCV 2016, pages 235–251, Cham, 2016. Springer International Publishing. ISBN 978-3…
  34. Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Muñoz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, et al. The stack: 3 tb of permissively licensed source code. arXiv preprint arXiv:2211.15533, 2022. find
  35. Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. Grounding language models to images for multimodal inputs and outputs, 2023. find
  36. Vik Korrapati. Moondream. Online, 2024. https://moondream.ai/. Accessed: 2025-03-27. ↗
  37. Hugo Laurençon, Lucile Saulnier, Leo Tronchon, Stas Bekman, Amanpreet Singh, Anton Lozhkov, Thomas Wang, Siddharth Karamcheti, Alexander M Rush, Douwe Kiela, Matthieu Cord, and Victor Sanh. OBELICS: An open web-scale filtered dataset of interleaved image-text documents. In Thirty-seventh Conference…
  38. Hugo Laurençon, Léo Tronchon, Matthieu Cord, and Victor Sanh. What matters when building vision-language models? arXiv preprint arXiv:2405.02246, 2024.
  39. Hugo Laurençon, Andrés Marafioti, Victor Sanh, and Léo Tronchon. Building and better understanding vision-language models: insights and future directions, 2024. https://arxiv.org/abs/2408.12637. — [arXiv:2408.12637](https://arxiv.org/abs/2408.12637) ↗
  40. Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Gadre, Hritik Bansal, Etash Guha, Sedrick Keh, Kushal Arora, et al. Datacomp-LM: In search of the next generation of training sets for language models. arXiv preprint arXiv:2406.11794, 2024a.
  41. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org, 2023a.
  42. Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, Limin Wang, and Yu Qiao. Mvbench: A comprehensive multi-modal video understanding benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22195–…
  43. Rui Li, Xiaohan Wang, Yuhui Zhang, Zeyu Wang, and Serena Yeung-Levy. Temporal preference optimization for long-form video understanding. arXiv preprint arXiv:2501.13919, 2025a. — [arXiv:2501.13919](https://arxiv.org/abs/2501.13919) find
  44. Yuanzhi Li, Sébastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. Textbooks are all you need ii: phi-1.5 technical report. arXiv preprint arXiv:2309.05463, 2023b.
  45. Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, and Jiebo Luo. Tgif: A new dataset and benchmark on animated gif description. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4641–4650, 2016. find
  46. 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, 2025b. — [arXiv:2501.14818](https://arxiv.org/abs/2501.14818) find
  47. Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122, 2023a.
  48. Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, et al. Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575, 2023b. — [arXiv:2311.07575](https://arxiv.org/abs/2311.07575) find
  49. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. https://openreview.net/forum?id=w0H2xGHlkw. ↗
  50. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. Llava-next: Improved reasoning, ocr, and world knowledge, January 2024a. https://llava-vl.github.io/blog/2024-01-30-llava-next/. ↗
  51. Jiajun Liu, Yibing Wang, Hanghang Ma, Xiaoping Wu, Xiaoqi Ma, Xiaoming Wei, Jianbin Jiao, Enhua Wu, and Jie Hu. Kangaroo: A powerful video-language model supporting long-context video input. arXiv preprint arXiv:2408.15542, 2024b. — [arXiv:2408.15542](https://arxiv.org/abs/2408.15542) find
  52. Xiaoran Liu, Hang Yan, Shuo Zhang, Chenxin An, Xipeng Qiu, and Dahua Lin. Scaling laws of rope-based extrapolation, 2024c. https://arxiv.org/abs/2310.05209. ↗
  53. Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, Lei Li, Sishuo Chen, Xu Sun, and Lu Hou. Tempcompass: Do video llms really understand videos?, 2024d. https://arxiv.org/abs/2403.00476. ↗
  54. Yuliang Liu, Zhang Li, Mingxin Huang, Biao Yang, Wenwen Yu, Chunyuan Li, Xu-Cheng Yin, Cheng-Lin Liu, Lianwen Jin, and Xiang Bai. Ocrbench: on the hidden mystery of ocr in large multimodal models. Science China Information Sciences, 67(12):220102, 2024e.
  55. Zhijian Liu, Ligeng Zhu, Baifeng Shi, Zhuoyang Zhang, Yuming Lou, Shang Yang, Haocheng Xi, Shiyi Cao, Yuxian Gu, Dacheng Li, et al. Nvila: Efficient frontier visual language models. arXiv preprint arXiv:2412.04468, 2024f. find
  56. 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, 2024g. — [arXiv:2409.12961](https://arxiv.org/abs/2409.12961) find
  57. Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, et al. Docling: An efficient open-source toolkit for ai-driven document conversion. In AAAI 25: Workshop on Open-Source AI for Mainstream Us… find
  58. Alejandro Lozano, Min Woo Sun, James Burgess, Jeffrey J. Nirschl, Christopher Polzak, Yuhui Zhang, Liangyu Chen, Jeffrey Gu, Ivan Lopez, Josiah Aklilu, Anita Rau, Austin Wolfgang Katzer, Collin Chiu, Orr Zohar, Xiaohan Wang, Alfred Seunghoon Song, Chiang Chia-Chun, Robert Tibshirani, and Serena Yeun… — [arXiv:2503.22727](https://arxiv.org/abs/2503.22727) find
  59. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Yaofeng Sun, et al. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525, 2024a.
  60. 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. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advan… find
  61. 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. In International Conference on Learning Representations (ICLR), 2024b.
  62. Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424, 2023.
  63. Ahmed Masry, Do Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. ChartQA: A benchmark for question answering about charts with visual and logical reasoning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2263–2279, Dublin, Ireland, May 2022. Association for Computati…
  64. Minesh Mathew, Dimosthenis Karatzas, and C. V. Jawahar. Docvqa: A dataset for vqa on document images. In 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 2199–2208, 2021. doi: 10.1109/WACV48630.2021.00225.
  65. Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier Biard, Sam Dodge, Philipp Dufter, Bowen Zhang, Dhruti Shah, Xianzhi Du, Futang Peng, Haotian Zhang, Floris Weers, Anton Belyi, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu He, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong… — [arXiv:2403.09611](https://arxiv.org/abs/2403.09611) find
  66. Ahmed Nassar, Andres Marafioti, Matteo Omenetti, Maksym Lysak, Nikolaos Livathinos, Christoph Auer, Lucas Morin, Rafael Teixeira de Lima, Yusik Kim, A. Said Gurbuz, Michele Dolfi, Miquel Farré, and Peter W. J. Staar. Smoldocling: An ultra-compact vision-language model for end-to-end multi-modal docu… — [arXiv:2503.11576](https://arxiv.org/abs/2503.11576) find
  67. Ahmed Nassar, Andres Marafioti, Matteo Omenetti, Maksym Lysak, Nikolaos Livathinos, Christoph Auer, Lucas Morin, Rafael Teixeira de Lima, Yusik Kim, A Said Gurbuz, et al. Smoldocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion. arXiv preprint arXiv:2503.115… — [arXiv:2503.11576](https://arxiv.org/abs/2503.11576) find
  68. OpenAI, :, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, Andre… — OpenAI o1 System Card
  69. Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Hamza Alobeidli, Alessandro Cappelli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. The RefinedWeb dataset for Falcon LLM: Outperforming curated corpora with web data only. In Advances in Neural Information Processing… find
  70. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision. In International Conference on Machine Lear…
  71. Weiming Ren, Huan Yang, Jie Min, Cong Wei, and Wenhu Chen. Vista: Enhancing long-duration and high-resolution video understanding by video spatiotemporal augmentation, 2024. https://arxiv.org/abs/2412.00927. — [arXiv:2412.00927](https://arxiv.org/abs/2412.00927) ↗
  72. 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. — [arXiv:2408.15998](https://arxiv.org/abs/2408.15998) find
  73. Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes Totz, Andrew P. Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, 2016. https://arxiv.org/abs/1609.05158. ↗
  74. Yan Shu, Zheng Liu, Peitian Zhang, Minghao Qin, Junjie Zhou, Zhengyang Liang, Tiejun Huang, and Bo Zhao. Video-xl: Extra-long vision language model for hour-scale video understanding. arXiv preprint arXiv:2409.14485, 2024. find
  75. Amanpreet Singh, Vivek Natarjan, Meet Shah, Yu Jiang, Xinlei Chen, Devi Parikh, and Marcus Rohrbach. Towards vqa models that can read. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8317–8326, 2019. find
  76. Luca Soldaini, Rodney Kinney, Akshita Bhagia, Dustin Schwenk, David Atkinson, Russell Authur, Ben Bogin, Khyathi Chandu, Jennifer Dumas, Yanai Elazar, Valentin Hofmann, Ananya Harsh Jha, Sachin Kumar, Li Lucy, Xinxi Lyu, Nathan Lambert, Ian Magnusson, Jacob Morrison, Niklas Muennighoff, Aakanksha Na… find
  77. Enxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Haozhe Chi, Xun Guo, Tian Ye, Yanting Zhang, Yan Lu, Jenq-Neng Hwang, and Gaoang Wang. Moviechat: From dense token to sparse memory for long video understanding, 2024. https://arxiv.org/abs/2307.16449. ↗
  78. Andreas Steiner, André Susano Pinto, Michael Tschannen, Daniel Keysers, Xiao Wang, Yonatan Bitton, Alexey Gritsenko, Matthias Minderer, Anthony Sherbondy, Shangbang Long, Siyang Qin, Reeve Ingle, Emanuele Bugliarello, Sahar Kazemzadeh, Thomas Mesnard, Ibrahim Alabdulmohsin, Lucas Beyer, and Xiaohua… — [arXiv:2412.03555](https://arxiv.org/abs/2412.03555) find
  79. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. Gemma 2: Improving open language models at a practical size, 2024. URL https://arxiv.org/abs/2408.00118, 1(3), 2024. ↗
  80. Peter Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Adithya Jairam Vedagiri IYER, Sai Charitha Akula, Shusheng Yang, Jihan Yang, Manoj Middepogu, Ziteng Wang, et al. Cambrian-1: A fully open, vision-centric exploration of multimodal llms. Advances in Neural Information Processing Systems, 37:87310–87…
  81. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. Llama: Open and efficient foundation language models, 2023.
  82. 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, 2024a.
  83. Xiaohan Wang, Yuhui Zhang, Orr Zohar, and Serena Yeung-Levy. Videoagent: Long-form video understanding with large language model as agent. In European Conference on Computer Vision, pages 58–76. Springer, 2024b. find
  84. Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wan… — DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  85. Jun Xu, Tao Mei, Ting Yao, and Yong Rui. Msr-vtt: A large video description dataset for bridging video and language. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5288–5296, 2016. find
  86. Zhangchen Xu, Fengqing Jiang, Luyao Niu, Yuntian Deng, Radha Poovendran, Yejin Choi, and Bill Yuchen Lin. Magpie: Alignment data synthesis from scratch by prompting aligned llms with nothing. arXiv preprint arXiv:2406.08464, 2024.
  87. Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, and Hai Zhao. Vript: A video is worth thousands of words, 2024. https://arxiv.org/abs/2406.06040. — [arXiv:2406.06040](https://arxiv.org/abs/2406.06040) ↗
  88. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, Qianyu Chen, Huarong Zhou, Zhensheng Zou, Haoye Zhang, Shengding Hu, Zhi Zheng, Jie Zhou, Jie Cai, Xu Han, Guoyang Zeng, Dahai Li, Zhiyuan Liu, and Maosong Sun. Minicpm-v: A gpt-4v leve… — MiniCPM-V: A GPT-4V Level MLLM on Your Phone
  89. Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, et al. Ureader: Universal ocr-free visually-situated language understanding with multimodal large language model. arXiv preprint arXiv:2310.05126, 2023.
  90. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. Mmmu: A massive multi-discipline… — MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
  91. Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. Mammoth: Building math generalist models through hybrid instruction tuning, 2023. URL https://arxiv.org/abs/2309.05653, 2024b. ↗
  92. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid loss for language image pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 11975–11986, 2023.
  93. Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, et al. Videollama 3: Frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106, 2025. — [arXiv:2501.13106](https://arxiv.org/abs/2501.13106) find
  94. Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, and Chunyuan Li. Video instruction tuning with synthetic data, 2024. https://arxiv.org/abs/2410.02713. ↗
  95. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36, 2024.
  96. 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.
  97. Orr Zohar, Xiaohan Wang, Yonatan Bitton, Idan Szpektor, and Serena Yeung-Levy. Video-star: Self-training enables video instruction tuning with any supervision, 2024a. https://arxiv.org/abs/2407.06189. — [arXiv:2407.06189](https://arxiv.org/abs/2407.06189) ↗
  98. Orr Zohar, Xiaohan Wang, Yann Dubois, Nikhil Mehta, Tong Xiao, Philippe Hansen-Estruch, Licheng Yu, Xiaofang Wang, Felix Juefei-Xu, Ning Zhang, et al. Apollo: An exploration of video understanding in large multimodal models. arXiv preprint arXiv:2412.10360, 2024b. — [arXiv:2412.10360](https://arxiv.org/abs/2412.10360) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/marafioti-2025-smolvlm-redefining-small-efficient-multimodal/