Image-text Model¶

@misc{zhang2024gme,
      title={GME: Improving Universal Multimodal Retrieval by Multimodal LLMs},
      author={Zhang, Xin and Zhang, Yanzhao and Xie, Wen and Li, Mingxin and Dai, Ziqi and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Li, Wenjie and Zhang, Min},
      year={2024},
      eprint={2412.16855},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={http://arxiv.org/abs/2412.16855}
}

@misc{zhang2024gme,
      title={GME: Improving Universal Multimodal Retrieval by Multimodal LLMs},
      author={Zhang, Xin and Zhang, Yanzhao and Xie, Wen and Li, Mingxin and Dai, Ziqi and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Li, Wenjie and Zhang, Min},
      year={2024},
      eprint={2412.16855},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={http://arxiv.org/abs/2412.16855}
}

@misc{ops_colqwen3_4b,
  author       = {OpenSearch-AI},
  title        = {Ops-ColQwen3: State-of-the-Art Multimodal Embedding Model for Visual Document Retrieval},
  year         = {2026},
  url          = {https://huggingface.co/OpenSearch-AI/Ops-ColQwen3-4B},
}

@article{qwen3vlembedding,
  title={Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking},
  author={Li, Mingxin and Zhang, Yanzhao and Long, Dingkun and Chen Keqin and Song, Sibo and Bai, Shuai and Yang, Zhibo and Xie, Pengjun and Yang, An and Liu, Dayiheng and Zhou, Jingren and Lin, Junyang},
  journal={arXiv preprint arXiv:2601.04720},
  year={2026}
}

@article{qwen3vlembedding,
  title={Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking},
  author={Li, Mingxin and Zhang, Yanzhao and Long, Dingkun and Chen Keqin and Song, Sibo and Bai, Shuai and Yang, Zhibo and Xie, Pengjun and Yang, An and Liu, Dayiheng and Zhou, Jingren and Lin, Junyang},
  journal={arXiv preprint arXiv:2601.04720},
  year={2026}
}

@article{jiang2024vlm2vec,
  title={VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks},
  author={Jiang, Ziyan and Meng, Rui and Yang, Xinyi and Yavuz, Semih and Zhou, Yingbo and Chen, Wenhu},
  journal={arXiv preprint arXiv:2410.05160},
  year={2024}
}

@article{jiang2024vlm2vec,
  title={VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks},
  author={Jiang, Ziyan and Meng, Rui and Yang, Xinyi and Yavuz, Semih and Zhou, Yingbo and Chen, Wenhu},
  journal={arXiv preprint arXiv:2410.05160},
  year={2024}
}

@misc{huang2025tomoro_colqwen3_embed,
  title={TomoroAI/tomoro-colqwen3-embed},
  author={Xin Huang and Kye Min Tan and Albert Phelps},
  year={2025},
  url={https://huggingface.co/TomoroAI/tomoro-colqwen3-embed-8b}
}

@misc{huang2025tomoro_colqwen3_embed,
  title={TomoroAI/tomoro-colqwen3-embed},
  author={Xin Huang and Kye Min Tan and Albert Phelps},
  year={2025},
  url={https://huggingface.co/TomoroAI/tomoro-colqwen3-embed-8b}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{sauerkrautlm-colpali-2025,
  title={SauerkrautLM-ColPali: Multi-Vector Vision Retrieval Models},
  author={David Golchinfar},
  organization={VAGO Solutions},
  year={2025},
  url={https://github.com/VAGOsolutions/sauerkrautlm-colpali}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@article{EagerEmbed,
  title={Eager Embed V1: Multimodal Dense Embeddings for Retrieval},
  author={Juan Pablo Balarini},
  year={2025},
  publisher={Eagerworks},
  url={https://github.com/eagerworks/eager-embed},
}

@article{karlinsky2025granitevision,
  title={Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence},
  author={Granite Vision Team and Karlinsky, Leonid and Arbelle, Assaf and Daniels, Abraham and Nassar, Ahmed and Alfassi, Amit and Wu, Bo and Schwartz, Eli and Joshi, Dhiraj and Kondic, Jovana and Shabtay, Nimrod and Li, Pengyuan and Herzig, Roei and Abedin, Shafiq and Perek, Shaked and Harary, Sivan and Barzelay, Udi and Raz Goldfarb, Adi and Oliva, Aude and Wieles, Ben and Bhattacharjee, Bishwaranjan and Huang, Brandon and Auer, Christoph and Gutfreund, Dan and Beymer, David and Wood, David and Kuehne, Hilde and Hansen, Jacob and Shtok, Joseph and Wong, Ken and Bathen, Luis Angel and Mishra, Mayank and Lysak, Maksym and Dolfi, Michele and Yurochkin, Mikhail and Livathinos, Nikolaos and Harel, Nimrod and Azulai, Ophir and Naparstek, Oshri and de Lima, Rafael Teixeira and Panda, Rameswar and Doveh, Sivan and Gupta, Shubham and Das, Subhro and Zawad, Syed and Kim, Yusik and He, Zexue and Brooks, Alexander and Goodhart, Gabe and Govindjee, Anita and Leist, Derek and Ibrahim, Ibrahim and Soffer, Aya and Cox, David and Soule, Kate and Lastras, Luis and Desai, Nirmit and Ofek-koifman, Shila and Raghavan, Sriram and Syeda-Mahmood, Tanveer and Staar, Peter and Drory, Tal and Feris, Rogerio},
  journal={arXiv preprint arXiv:2502.09927},
  year={2025}
}

@article{chen2025mmE5,
  title={mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data},
  author={Chen, Haonan and Wang, Liang and Yang, Nan and Zhu, Yutao and Zhao, Ziliang and Wei, Furu and Dou, Zhicheng},
  journal={arXiv preprint arXiv:2502.08468},
  year={2025}
}

@article{koukounas2024jinaclip,
  title={Jina CLIP: Your CLIP Model Is Also Your Text Retriever},
  author={Koukounas, Andreas and Mastrapas, Georgios and Günther, Michael and Wang, Bo and Martens, Scott and Mohr, Isabelle and Sturua, Saba and Akram, Mohammad Kalim and Martínez, Joan Fontanals and Ognawala, Saahil and Guzman, Susana and Werk, Maximilian and Wang, Nan and Xiao, Han},
  journal={arXiv preprint arXiv:2405.20204},
  year={2024}
}

@misc{günther2025jinaembeddingsv4universalembeddingsmultimodal,
      title={jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval},
      author={Michael Günther and Saba Sturua and Mohammad Kalim Akram and Isabelle Mohr and Andrei Ungureanu and Sedigheh Eslami and Scott Martens and Bo Wang and Nan Wang and Han Xiao},
      year={2025},
      eprint={2506.18902},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2506.18902},
}

@misc{huang2024llm2clippowerfullanguagemodel,
  title={LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation},
  author={Weiquan Huang and Aoqi Wu and Yifan Yang and Xufang Luo and Yuqing Yang and Liang Hu and Qi Dai and Xiyang Dai and Dongdong Chen and Chong Luo and Lili Qiu},
  year={2024},
  eprint={2411.04997},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2411.04997}
}

@misc{huang2024llm2clippowerfullanguagemodel,
  title={LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation},
  author={Weiquan Huang and Aoqi Wu and Yifan Yang and Xufang Luo and Yuqing Yang and Liang Hu and Qi Dai and Xiyang Dai and Dongdong Chen and Chong Luo and Lili Qiu},
  year={2024},
  eprint={2411.04997},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2411.04997}
}

@misc{huang2024llm2clippowerfullanguagemodel,
  title={LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation},
  author={Weiquan Huang and Aoqi Wu and Yifan Yang and Xufang Luo and Yuqing Yang and Liang Hu and Qi Dai and Xiyang Dai and Dongdong Chen and Chong Luo and Lili Qiu},
  year={2024},
  eprint={2411.04997},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2411.04997}
}

@misc{nomicembedmultimodal2025,
  title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
  author={Nomic Team},
  year={2025},
  publisher={Nomic AI},
  url={https://nomic.ai/blog/posts/nomic-embed-multimodal}
}

@misc{nomicembedmultimodal2025,
  title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
  author={Nomic Team},
  year={2025},
  publisher={Nomic AI},
  url={https://nomic.ai/blog/posts/nomic-embed-multimodal}
}

@misc{nomicembedmultimodal2025,
  title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
  author={Nomic Team},
  year={2025},
  publisher={Nomic AI},
  url={https://www.nomic.ai/news/nomic-embed-multimodal}
}

@misc{nomicembedmultimodal2025,
  title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
  author={Nomic Team},
  year={2025},
  publisher={Nomic AI},
  url={https://www.nomic.ai/news/nomic-embed-multimodal}
}

@article{nussbaum2024nomicembedvision,
      title={Nomic Embed Vision: Expanding the Latent Space},
      author={Nussbaum, Zach and Duderstadt, Brandon and Mulyar, Andriy},
      journal={arXiv preprint arXiv:2406.18587},
      year={2024},
      eprint={2406.18587},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2406.18587}
}

@misc{xu2025llamanemoretrievercolembedtopperforming,
      title={Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model},
      author={Mengyao Xu and Gabriel Moreira and Ronay Ak and Radek Osmulski and Yauhen Babakhin and Zhiding Yu and Benedikt Schifferer and Even Oldridge},
      year={2025},
      eprint={2507.05513},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.05513}
}

@misc{xu2025llamanemoretrievercolembedtopperforming,
      title={Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model},
      author={Mengyao Xu and Gabriel Moreira and Ronay Ak and Radek Osmulski and Yauhen Babakhin and Zhiding Yu and Benedikt Schifferer and Even Oldridge},
      year={2025},
      eprint={2507.05513},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.05513}
}

@misc{moreira2026nemotroncolembedv2topperforming,
    title={Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval},
    author={Gabriel de Souza P. Moreira and Ronay Ak and Mengyao Xu and Oliver Holworthy and Benedikt Schifferer and Zhiding Yu and Yauhen Babakhin and Radek Osmulski and Jiarui Cai and Ryan Chesler and Bo Liu and Even Oldridge},
    year={2026},
    eprint={2602.03992},
    archivePrefix={arXiv},
    primaryClass={cs.IR},
    url={https://arxiv.org/abs/2602.03992},
}

@misc{ronay2026smallyetmighty,
    title={Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models},
    author={Ronay Ak, Gabriel de Souza Pereira Moreira and Bo Liu},
    year={2026},
    howpublished = {Available at: https://huggingface.co/blog/nvidia/llama-nemotron-vl-1b},
}

@misc{moreira2026nemotroncolembedv2topperforming,
    title={Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval},
    author={Gabriel de Souza P. Moreira and Ronay Ak and Mengyao Xu and Oliver Holworthy and Benedikt Schifferer and Zhiding Yu and Yauhen Babakhin and Radek Osmulski and Jiarui Cai and Ryan Chesler and Bo Liu and Even Oldridge},
    year={2026},
    eprint={2602.03992},
    archivePrefix={arXiv},
    primaryClass={cs.IR},
    url={https://arxiv.org/abs/2602.03992},
}

@misc{moreira2026nemotroncolembedv2topperforming,
    title={Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval},
    author={Gabriel de Souza P. Moreira and Ronay Ak and Mengyao Xu and Oliver Holworthy and Benedikt Schifferer and Zhiding Yu and Yauhen Babakhin and Radek Osmulski and Jiarui Cai and Ryan Chesler and Bo Liu and Even Oldridge},
    year={2026},
    eprint={2602.03992},
    archivePrefix={arXiv},
    primaryClass={cs.IR},
    url={https://arxiv.org/abs/2602.03992},
}

@article{jiang2024e5v,
      title={E5-V: Universal Embeddings with Multimodal Large Language Models},
      author={Jiang, Ting and Song, Minghui and Zhang, Zihan and Huang, Haizhen and Deng, Weiwei and Sun, Feng and Zhang, Qi and Wang, Deqing and Zhuang, Fuzhen},
      journal={arXiv preprint arXiv:2407.12580},
      year={2024},
      eprint={2407.12580},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.12580}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@misc{faysse2024colpali,
  title={ColPali: Efficient Document Retrieval with Vision Language Models},
  author={Faysse, Manuel and Sibille, Hugues and Wu, Tony and Omrani, Bilel and Viaud, Gautier and Hudelot, C'eline and Colombo, Pierre},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR}
}

@article{zhou2024vista,
  title={VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval},
  author={Zhou, Junjie and Liu, Zheng and Xiao, Shitao and Zhao, Bo and Xiong, Yongping},
  journal={arXiv preprint arXiv:2406.04292},
  year={2024}
}

@article{zhou2024vista,
  title={VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval},
  author={Zhou, Junjie and Liu, Zheng and Xiao, Shitao and Zhao, Bo and Xiong, Yongping},
  journal={arXiv preprint arXiv:2406.04292},
  year={2024}
}

@article{EVA-CLIP,
      title={EVA-CLIP: Improved Training Techniques for CLIP at Scale},
      author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
      journal={arXiv preprint arXiv:2303.15389},
      year={2023}
}

@article{EVA-CLIP,
      title={EVA-CLIP: Improved Training Techniques for CLIP at Scale},
      author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
      journal={arXiv preprint arXiv:2303.15389},
      year={2023}
}

@article{EVA-CLIP,
      title={EVA-CLIP: Improved Training Techniques for CLIP at Scale},
      author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
      journal={arXiv preprint arXiv:2303.15389},
      year={2023}
}

@article{EVA-CLIP,
      title={EVA-CLIP: Improved Training Techniques for CLIP at Scale},
      author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
      journal={arXiv preprint arXiv:2303.15389},
      year={2023}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2201.12086,
    doi = {10.48550/ARXIV.2201.12086},
    url = {https://arxiv.org/abs/2201.12086},
    author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

@inproceedings{li2023blip2,
    title={{BLIP-2:} Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models},
    author={Junnan Li and Dongxu Li and Silvio Savarese and Steven Hoi},
    year={2023},
    booktitle={ICML},
}

@inproceedings{li2023blip2,
    title={{BLIP-2:} Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models},
    author={Junnan Li and Dongxu Li and Silvio Savarese and Steven Hoi},
    year={2023},
    booktitle={ICML},
}

@article{xu2025metaclip2,
  title={MetaCLIP 2: A Worldwide Scaling Recipe},
  author={Xu, Hu and Xie, Saining and Ghosh, Gargi and Kira, Zsolt and Darrell, Trevor},
  journal={arXiv preprint arXiv:2507.22062},
  year={2025}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{zhai2023sigmoid,
      title={Sigmoid Loss for Language Image Pre-Training},
      author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
      year={2023},
      eprint={2303.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{koukounas2024jinaclipv2multilingualmultimodalembeddings,
      title={jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images},
      author={Andreas Koukounas and Georgios Mastrapas and Bo Wang and Mohammad Kalim Akram and Sedigheh Eslami and Michael Günther and Isabelle Mohr and Saba Sturua and Scott Martens and Nan Wang and Han Xiao},
      year={2024},
      eprint={2412.08802},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.08802},
}

@misc{kakaobrain2022coyo-align,
    title         = {COYO-ALIGN},
    author        = {Yoon, Boogeo and Lee, Youhan and Baek, Woonhyuk},
    year          = {2022},
    howpublished  = {https://github.com/kakaobrain/coyo-align},
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@inproceedings{cherti2023reproducible,
    title={Reproducible scaling laws for contrastive language-image learning},
    author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2818--2829},
    year={2023}
}

@article{nanovdr2026,
  title={NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval},
  author={Liu, Zhuchenyang and Zhang, Yao and Xiao, Yu},
  journal={arXiv preprint arXiv:2603.12824},
  year={2026}
}

@article{radford2021learning,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya},
  journal={arXiv preprint arXiv:2103.00020},
  year={2021}
}

@article{radford2021learning,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya},
  journal={arXiv preprint arXiv:2103.00020},
  year={2021}
}

@article{radford2021learning,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya},
  journal={arXiv preprint arXiv:2103.00020},
  year={2021}
}