Elamur Research⌕
☰
home / papers / 2024 / ColPali: Efficient Document Retrieval with Vision Language Models

ColPali: Efficient Document Retrieval with Vision Language Models

Paper · 2024 · Manuel Faysse, Hugues Sibille, Tony Wu et al.

Summary

Standard retrieval over PDFs relies on a long ingestion chain: OCR or PDF parsing, layout detection, chunking, and sometimes captioning of figures. This chain is slow and fragile, and it mostly ignores visual information such as tables, charts and page layout. The authors first build ViDoRe, a page-level benchmark for visually rich document retrieval. It covers several domains, modalities and two languages (English and French). It combines repurposed VQA datasets with new topic-specific collections whose queries were generated by Claude-3 Sonnet. They then propose ColPali, which skips text extraction entirely. A Vision Language Model built on PaliGemma-3B turns each page image into many patch-level embeddings, and queries are compared to these embeddings with ColBERT-style late interaction (MaxSim). On ViDoRe, ColPali clearly outperforms modern text-based pipelines. It is also simpler, indexes pages faster and can be trained end to end. This matters for RAG and enterprise search, where much of the key information sits in visual elements. Models, data, code and a public leaderboard are openly released.

Key points

  • ViDoRe has two groups of tasks:
    • Academic tasks: DocVQA, InfoVQA, TAT-DQA, arXiVQA and TabFQuAD (500–1,600 queries each).
    • Practical tasks: Energy, Government, Healthcare, AI and Shift Project, each with 100 queries over 1,000 pages.
  • TabFQuAD is a new human-labeled French dataset built from tables in industrial PDFs (210 queries). It is released together with the paper.
  • ColPali's backbone is PaliGemma-3B, which projects SigLIP-So400m/14 patch embeddings into the vector space of Gemma-2B. Its text model uses full-block attention over the prefix (instruction text and image tokens).
  • The authors set three requirements for efficient retrieval systems: (R1) strong retrieval quality, (R2) low online query latency and (R3) high indexing throughput.
  • Similarity maps link query tokens to the relevant image patches, for example "Kazakhstan" and the nearby "Kashagan" oil field. All resources are available at hf.co/vidore.

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

🎓ETH ZurichZurich · Switzerland84 works · 9,181 citations🔬CentraleSupélecGif-sur-Yvette · France12 works · 1,545 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksComputer Vision and Pattern Recognition · 3,486 worksInformation Systems · 1,730 works

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3,894 worksVision & language · 811 worksInformation retrieval & search · 552 works

Cite

Cite as Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Celine Hudelot and Pierre Colombo. 2024. ColPali: Efficient Document Retrieval with Vision Language Models. arXiv:2407.01449.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2407.01449 · arXiv 2407.01449

@misc{faysse2024colpali,
  title = {{ColPali: Efficient Document Retrieval with Vision Language Models}},
  author = {Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Celine Hudelot and Pierre Colombo},
  year = {2024},
  doi = {10.48550/arxiv.2407.01449},
  eprint = {2407.01449},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2407.01449}
}

References

61 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ibrahim Alabdulmohsin, Xiaohua Zhai, Alexander Kolesnikov, and Lucas Beyer. Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design. 2023. doi: 10.48550/ARXIV.2305. 13035. URL https://arxiv.org/abs/2305.13035. Publisher: arXiv Version Number: 5. — [doi:10.48550/arxiv.2305](https://doi.org/10.48550/arxiv.2305) ↗
  2. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katie Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob Menick, Sebastian Borgeaud, Andrew Brock… — Flamingo: a Visual Language Model for Few-Shot Learning
  3. Anthropic. The Claude 3 Model Family: Opus, Sonnet, Haiku, 2024. https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/ Model Card Claude 3.pdf. ↗
  4. URL Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R. Manmatha. DocFormer: End-to-End Transformer for Document Understanding, 2021. URL https://arxiv.org/abs/ 2106.11539. Version Number: 2. ↗
  5. 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. 2023. doi: 10.48550/ARXIV.2308.12966. URL https://arxiv.org/abs/2308.12966. Publish… ↗
  6. Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset, 2016. URL https://arxi…
  7. Lucas Beyer, Andreas Steiner, André Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, Thomas Unterthiner, Daniel Keysers, Skanda Koppula, Fangyu Liu, Adam Grycner, Alexey Gritsenko, Neil Houlsby, Manoj Kumar, K… — PaliGemma: A versatile 3B VLM for transfer
  8. Burton H. Bloom. Space/time trade-offs in hash coding with allowable errors. Commun. ACM, 13(7): 422–426, July 1970. ISSN 0001-0782. doi: 10.1145/362686.362692. URL https://doi.org/ 10.1145/362686.362692. Place: New York, NY, USA Publisher: Association for Computing Machinery. — [doi:10.1145/362686.362692](https://doi.org/10.1145/362686.362692) find
  9. Łukasz Borchmann, Michał Pietruszka, Tomasz Stanislawek, Dawid Jurkiewicz, Michał Turski, Karolina Szyndler, and Filip Graliński. DUE: End-to-End Document Understanding Benchmark. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), 2021. URL… find
  10. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation, 2024. URL https://arxiv.org/abs/2402.03216. Version Number: 3. ↗
  11. Xi Chen, Xiao Wang, Lucas Beyer, Alexander Kolesnikov, Jialin Wu, Paul Voigtlaender, Basil Mustafa, Sebastian Goodman, Ibrahim Alabdulmohsin, Piotr Padlewski, Daniel Salz, Xi Xiong, Daniel Vlasic, Filip Pavetic, Keran Rong, Tianli Yu, Daniel Keysers, Xiaohua Zhai, and Radu Soricut. PaLI-3 Vision Lan… — [arXiv:2310.09199](https://arxiv.org/abs/2310.09199) find
  12. Benjamin Clavié, Antoine Chaffin, and Griffin Adams. Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling, 2024. URL https://arxiv.org/ abs/2409.14683. Version Number: 1. — [arXiv:2409.14683](https://arxiv.org/abs/2409.14683) ↗
  13. Cohere. Introducing Rerank 3: A New Foundation Model for Efficient Enterprise Search & Retrieval, April 2024. URL https://cohere.com/blog/rerank-3. ↗
  14. Tri Dao. Flashattention-2: Faster attention with better parallelism and work partitioning, 2023. URL https://arxiv.org/abs/2307.08691. ↗
  15. Timothée Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. Vision Transformers Need Registers. 2023. doi: 10.48550/ARXIV.2309.16588. URL https://arxiv.org/abs/2309. 16588. Publisher: [object Object] Version Number: 2. — [doi:10.48550/arxiv.2309.16588](https://doi.org/10.48550/arxiv.2309.16588) ↗
  16. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, 2018. URL https://arxiv.org/abs/ 1810.04805. Version Number: 2. ↗
  17. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. 2020. doi: 10.4…
  18. Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. YOLOX: Exceeding YOLO Series in 2021, 2021. URL https://arxiv.org/abs/2107.08430. Version Number: 2. ↗
  19. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Léonard Hussenot, Pier Giuseppe Sessa, Aakanksha Chowdhery, Adam Roberts, Aditya Barua, Alex Botev, Alex Castro-Ros, Ambrose… find
  20. Hippolyte Gisserot-Boukhlef, Manuel Faysse, Emmanuel Malherbe, Céline Hudelot, and Pierre Colombo. Towards trustworthy reranking: A simple yet effective abstention mechanism, 2024. URL https://arxiv.org/abs/2402.12997. — [arXiv:2402.12997](https://arxiv.org/abs/2402.12997) ↗
  21. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. LoRA: Low-Rank Adaptation of Large Language Models. 2021. doi: 10.48550/ ARXIV.2106.09685. URL https://arxiv.org/abs/2106.09685. Publisher: arXiv Version Number: 2. ↗
  22. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking. 2022. doi: 10.48550/ARXIV.2204.08387. URL https://arxiv.org/abs/2204.08387. Publisher: arXiv Version Number: 3. ↗
  23. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroi… find
  24. Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. Vlm2vec: Training vision-language models for massive multimodal embedding tasks, 2024. URL https://arxiv.org/abs/2410.05160. — [arXiv:2410.05160](https://arxiv.org/abs/2410.05160) ↗
  25. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. Dense Passage Retrieval for Open-Domain Question Answering, 2020. URL https://arxiv.org/abs/2004.04906. Version Number: 3. ↗
  26. Omar Khattab and Matei Zaharia. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. 2020. doi: 10.48550/ARXIV.2004.12832. URL https://arxiv.org/abs/2004.12832. ↗
  27. Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, and Seunghyun Park. OCR-free Document Understanding Transformer, 2021. URL https://arxiv.org/abs/2111.15664. Version Number: 5. ↗
  28. Andreas Koukounas, Georgios Mastrapas, Michael Günther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Martı́nez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, and Han Xiao. Jina CLIP: Your CLIP Model Is Also Your Text Retriever, 2024. URL http… — [arXiv:2405.20204](https://arxiv.org/abs/2405.20204) find
  29. Hugo Laurençon, Andrés Marafioti, Victor Sanh, and Léo Tronchon. Building and better understanding vision-language models: insights and future directions., 2024a. find
  30. Hugo Laurençon, Léo Tronchon, Matthieu Cord, and Victor Sanh. What matters when building vision-language models?, May 2024b. URL http://arxiv.org/abs/2405.02246. arXiv:2405.02246 [cs]. ↗
  31. Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. Nv-embed: Improved techniques for training llms as generalist embedding models, 2024. URL https://arxiv.org/abs/2405.17428. ↗
  32. Jinhyuk Lee, Zhuyun Dai, Sai Meher Karthik Duddu, Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Y. Zhao. Rethinking the Role of Token Retrieval in Multi-Vector Retrieval, 2023. URL https://arxiv.org/abs/2304.01982. Version Number: 3. — [arXiv:2304.01982](https://arxiv.org/abs/2304.01982) ↗
  33. Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models, 2024.
  34. Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Dollár. Microsoft COCO: Common Objects in Context, 2014. URL https://arxiv.org/abs/1405.0312. Version Number: 3. ↗
  35. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual Instruction Tuning. 2023. doi: 10.48550/ARXIV.2304.08485. URL https://arxiv.org/abs/2304.08485. Publisher: arXiv Version Number: 1. ↗
  36. Lucas Beyer*, Andreas Steiner*, André Susano Pinto*, Alexander Kolesnikov*, Xiao Wang*, Xiaohua Zhai*, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Jeremiah Harmsen, Daniel Keysers, Neil Houlsby, Xi Chen, Emanuele Bugliarello, Thomas Unterthiner, Keran Rong, Matthias Minder… find
  37. Yubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, Pan Zhang, Liangming Pan, Yu-Gang Jiang, Jiaqi Wang, Yixin Cao, and Aixin Sun. Mmlongbench-doc: Benchmarking long-context document understanding with visualizations, 2024. URL https://arx…
  38. Minesh Mathew, Dimosthenis Karatzas, and C. V. Jawahar. DocVQA: A Dataset for VQA on Document Images. 2020. doi: 10.48550/ARXIV.2007.00398. URL https://arxiv.org/abs/ 2007.00398. ↗
  39. Minesh Mathew, Viraj Bagal, Rubèn Pérez Tito, Dimosthenis Karatzas, Ernest Valveny, and C. V Jawahar. InfographicVQA, 2021. URL https://arxiv.org/abs/2104.12756. Version Number: 2. — [arXiv:2104.12756](https://arxiv.org/abs/2104.12756) ↗
  40. Niklas Muennighoff, Nouamane Tazi, Loı̈c Magne, and Nils Reimers. MTEB: Massive Text Embedding Benchmark, 2022. URL https://arxiv.org/abs/2210.07316. Version Number: 3. ↗
  41. Nomic. Nomic Embed Vision: Expanding The Nomic Latent Space, June 2024. URL https://blog.nomic.ai/posts/nomic-embed-vision. ↗
  42. Averi Nowak, Francesco Piccinno, and Yasemin Altun. Multimodal chart retrieval: A comparison of text, table and image based approaches. In Kevin Duh, Helena Gomez, and Steven Bethard (eds.), Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguis… find
  43. 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. 2021. doi: 10.48550/ ARXIV.2103.00020. URL…
  44. Nils Reimers and Iryna Gurevych. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks, 2019. URL https://arxiv.org/abs/1908.10084. Version Number: 1. ↗
  45. Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. Okapi at TREC-3. In Donna K. Harman (ed.), Proceedings of The Third Text REtrieval Conference, TREC 1994, Gaithersburg, Maryland, USA, November 2-4, 1994, volume 500-225 of NIST Special Publication, pp. 10…
  46. Keshav Santhanam, Omar Khattab, Christopher Potts, and Matei Zaharia. PLAID: An Efficient Engine for Late Interaction Retrieval, 2022. URL https://arxiv.org/abs/2205.09707. Version Number: 1. ↗
  47. R. Smith. An Overview of the Tesseract OCR Engine. In Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2, pp. 629–633, Curitiba, Parana, Brazil, September 2007. IEEE. ISBN 978-0-7695-2822-9. doi: 10.1109/ICDAR.2007.4376991. URL http://ieeexplore.ieee.org/document/… — [doi:10.1109/icdar.2007.4376991](https://doi.org/10.1109/icdar.2007.4376991) ↗
  48. Karen Sparck Jones. A STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVAL. Journal of Documentation, 28(1):11–21, January 1972. ISSN 0022-0418. doi: 10.1108/eb026526. URL https://www.emerald.com/insight/content/doi/ 10.1108/eb026526/full/html. — [doi:10.1108/eb026526](https://doi.org/10.1108/eb026526) ↗
  49. Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, and Mohit Bansal. Unifying Vision, Text, and Layout for Universal Document Processing, 2022. URL https://arxiv.org/abs/2212.02623. Version Number: 3. ↗
  50. Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models, 2021. URL https://arxiv.org/abs/2104.08663. Version Number: 4. ↗
  51. Ashish V. Thapliyal, Jordi Pont-Tuset, Xi Chen, and Radu Soricut. Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset, 2022. URL https://arxiv.org/abs/2205.12522. Version Number: 2. ↗
  52. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. Text Embeddings by Weakly-Supervised Contrastive Pre-training, 2022. URL https://arxiv.org/abs/2212.03533. Version Number: 2. ↗
  53. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. Improving text embeddings with large language models, 2024a. URL https://arxiv.org/abs/2401. 00368. ↗
  54. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. Qwen2-vl: Enhancing vision-language model’s perception of the world a… — Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
  55. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers, April 2020. URL http://arxiv.org/abs/2002.10957. arXiv:2002.10957 [cs]. ↗
  56. Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. FILIP: Fine-grained Interactive Language-Image Pre-Training, 2021. URL https://arxiv.org/abs/2111.07783. Version Number: 1. — [arXiv:2111.07783](https://arxiv.org/abs/2111.07783) ↗
  57. 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
  58. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid Loss for Language Image Pre-Training. 2023. doi: 10.48550/ARXIV.2303.15343. URL https://arxiv.org/abs/ 2303.15343. Publisher: [object Object] Version Number: 4. ↗
  59. Li Zhang, Shuo Zhang, and Krisztian Balog. Table2vec: Neural word and entity embeddings for table population and retrieval. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’19. ACM, July 2019. doi: 10.1145/3331184.3331333. URL… — [doi:10.1145/3331184.3331333](https://doi.org/10.1145/3331184.3331333) find
  60. Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, and Shafiq Joty. Retrieving Multimodal Information for Augmented Generation: A Survey, 2023. URL https://arxiv.org/abs/2303.10868. Version Number: 3. ↗
  61. Fengbin Zhu, Wenqiang Lei, Fuli Feng, Chao Wang, Haozhou Zhang, and Tat-Seng Chua. Towards Complex Document Understanding By Discrete Reasoning. 2022. doi: 10.48550/ARXIV.2207. 11871. URL https://arxiv.org/abs/2207.11871. Publisher: arXiv Version Number: 3. — [doi:10.48550/arxiv.2207](https://doi.org/10.48550/arxiv.2207) ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/faysse-2024-colpali-efficient-document-retrieval-vision/