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}
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@inproceedings{zhou2024megapairs,
  address = {Vienna, Austria},
  author = {Zhou, Junjie and Xiong, Yongping and Liu, Zheng and Liu, Ze and Xiao, Shitao and Wang, Yueze and Zhao, Bo and Zhang, Chen Jason and Lian, Defu},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.935},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {19076--19095},
  publisher = {Association for Computational Linguistics},
  title = {{M}ega{P}airs: Massive Data Synthesis for Universal Multimodal Retrieval},
  url = {https://aclanthology.org/2025.acl-long.935/},
  year = {2025},
}

@misc{teiletche2025modernvbertsmallervisualdocument,
  title={ModernVBERT: Towards Smaller Visual Document Retrievers},
  author={Paul Teiletche and Quentin Macé and Max Conti and Antonio Loison and Gautier Viaud and Pierre Colombo and Manuel Faysse},
  year={2025},
  eprint={2510.01149},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2510.01149}
}

@misc{teiletche2025modernvbertsmallervisualdocument,
  title={ModernVBERT: Towards Smaller Visual Document Retrievers},
  author={Paul Teiletche and Quentin Macé and Max Conti and Antonio Loison and Gautier Viaud and Pierre Colombo and Manuel Faysse},
  year={2025},
  eprint={2510.01149},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2510.01149}
}

@misc{teiletche2025modernvbertsmallervisualdocument,
  title={ModernVBERT: Towards Smaller Visual Document Retrievers},
  author={Paul Teiletche and Quentin Macé and Max Conti and Antonio Loison and Gautier Viaud and Pierre Colombo and Manuel Faysse},
  year={2025},
  eprint={2510.01149},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2510.01149}
}

@article{wang2025virtue,
  title={VIRTUE: Visual-Interactive Text-Image Universal Embedder},
  author={Wang, Wei-Yao and Tateishi, Kazuya and Wu, Qiyu and Takahashi, Shusuke and Mitsufuji, Yuki},
  journal={arXiv preprint arXiv:2510.00523},
  year={2025}
}

@article{wang2025virtue,
  title={VIRTUE: Visual-Interactive Text-Image Universal Embedder},
  author={Wang, Wei-Yao and Tateishi, Kazuya and Wu, Qiyu and Takahashi, Shusuke and Mitsufuji, Yuki},
  journal={arXiv preprint arXiv:2510.00523},
  year={2025}
}

@inproceedings{jiang2024vlm2vec,
  archiveprefix = {arXiv},
  author = {Ziyan Jiang and Rui Meng and Xinyi Yang and Semih Yavuz and Yingbo Zhou and Wenhu Chen},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2410.05160},
  title = {{VLM}2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks},
  url = {https://openreview.net/forum?id=TE0KOzWYAF},
  year = {2025},
}

@inproceedings{jiang2024vlm2vec,
  archiveprefix = {arXiv},
  author = {Ziyan Jiang and Rui Meng and Xinyi Yang and Semih Yavuz and Yingbo Zhou and Wenhu Chen},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2410.05160},
  title = {{VLM}2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks},
  url = {https://openreview.net/forum?id=TE0KOzWYAF},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@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}
}

@inproceedings{chen2025mmE5,
  address = {Vienna, Austria},
  author = {Chen, Haonan and Wang, Liang and Yang, Nan and Zhu, Yutao and Zhao, Ziliang and Wei, Furu and Dou, Zhicheng},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2025},
  doi = {10.18653/v1/2025.findings-acl.433},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-256-5},
  month = {jul},
  pages = {8254--8275},
  publisher = {Association for Computational Linguistics},
  title = {mm{E}5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data},
  url = {https://aclanthology.org/2025.findings-acl.433/},
  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}
}

@inproceedings{günther2025jinaembeddingsv4universalembeddingsmultimodal,
  address = {Suzhuo, China},
  author = {G{\"u}nther, Michael and Sturua, Saba and Akram, Mohammad Kalim and Mohr, Isabelle and Ungureanu, Andrei and Wang, Bo and Eslami, Sedigheh and Martens, Scott and Werk, Maximilian and Wang, Nan and Xiao, Han},
  booktitle = {Proceedings of the 5th Workshop on Multilingual Representation Learning ({MRL} 2025)},
  doi = {10.18653/v1/2025.mrl-main.36},
  editor = {Adelani, David Ifeoluwa and Arnett, Catherine and Ataman, Duygu and Chang, Tyler A. and Gonen, Hila and Raja, Rahul and Schmidt, Fabian and Stap, David and Wang, Jiayi},
  isbn = {979-8-89176-345-6},
  month = {nov},
  pages = {531--550},
  publisher = {Association for Computational Linguistics},
  title = {jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval},
  url = {https://aclanthology.org/2025.mrl-main.36/},
  year = {2025},
}

@article{huang2024llm2clippowerfullanguagemodel,
  author = {Huang, Weiquan and Wu, Aoqi and Yang, Yifan and Luo, Xufang and Yang, Yuqing and Naseem, Usman and Wang, Chunyu and Dai, Qi and Dai, Xiyang and Chen, Dongdong and Luo, Chong and Qiu, Lili and Hu, Liang},
  doi = {10.1609/aaai.v40i7.37427},
  issn = {2159-5399},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  month = {Mar},
  number = {7},
  pages = {5131–5139},
  publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
  title = {LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation},
  url = {https://doi.org/10.1609/aaai.v40i7.37427},
  volume = {40},
  year = {2026},
}

@article{huang2024llm2clippowerfullanguagemodel,
  author = {Huang, Weiquan and Wu, Aoqi and Yang, Yifan and Luo, Xufang and Yang, Yuqing and Naseem, Usman and Wang, Chunyu and Dai, Qi and Dai, Xiyang and Chen, Dongdong and Luo, Chong and Qiu, Lili and Hu, Liang},
  doi = {10.1609/aaai.v40i7.37427},
  issn = {2159-5399},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  month = {Mar},
  number = {7},
  pages = {5131–5139},
  publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
  title = {LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation},
  url = {https://doi.org/10.1609/aaai.v40i7.37427},
  volume = {40},
  year = {2026},
}

@article{huang2024llm2clippowerfullanguagemodel,
  author = {Huang, Weiquan and Wu, Aoqi and Yang, Yifan and Luo, Xufang and Yang, Yuqing and Naseem, Usman and Wang, Chunyu and Dai, Qi and Dai, Xiyang and Chen, Dongdong and Luo, Chong and Qiu, Lili and Hu, Liang},
  doi = {10.1609/aaai.v40i7.37427},
  issn = {2159-5399},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  month = {Mar},
  number = {7},
  pages = {5131–5139},
  publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
  title = {LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation},
  url = {https://doi.org/10.1609/aaai.v40i7.37427},
  volume = {40},
  year = {2026},
}

@inproceedings{chen2025moca,
  address = {San Diego, California, United States},
  author = {Chen, Haonan and Liu, Hong and Luo, Yuping and Wang, Liang and Yang, Nan and Wei, Furu and Dou, Zhicheng},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2026.acl-long.34},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-390-6},
  month = {jul},
  pages = {810--823},
  publisher = {Association for Computational Linguistics},
  title = {{M}o{C}a: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings},
  url = {https://aclanthology.org/2026.acl-long.34/},
  year = {2026},
}

@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},
}

@inproceedings{moreira2025_nvretriever,
  author = {Moreira, Gabriel de Souza P. and Osmulski, Radek and Xu, Mengyao and Ak, Ronay and Schifferer, Benedikt and Oldridge, Even},
  title = {Improving Text Embedding Models with Positive-aware Hard-negative Mining},
  year = {2025},
  isbn = {9798400720406},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3746252.3761254},
  doi = {10.1145/3746252.3761254},
  pages = {2169–2178},
  numpages = {10},
  keywords = {contrastive learning, distillation, embedding models, hard-negative mining, rag, text retrieval, transformers},
  location = {Seoul, Republic of Korea},
  series = {CIKM '25},
}

@inproceedings{moreira2025_nvretriever,
  author = {Moreira, Gabriel de Souza P. and Osmulski, Radek and Xu, Mengyao and Ak, Ronay and Schifferer, Benedikt and Oldridge, Even},
  title = {Improving Text Embedding Models with Positive-aware Hard-negative Mining},
  year = {2025},
  isbn = {9798400720406},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3746252.3761254},
  doi = {10.1145/3746252.3761254},
  pages = {2169–2178},
  numpages = {10},
  keywords = {contrastive learning, distillation, embedding models, hard-negative mining, rag, text retrieval, transformers},
  location = {Seoul, Republic of Korea},
  series = {CIKM '25},
}

@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},
}

@inproceedings{yu2024visrag,
  archiveprefix = {arXiv},
  author = {Shi Yu and Chaoyue Tang and Bokai Xu and Junbo Cui and Junhao Ran and Yukun Yan and Zhenghao Liu and Shuo Wang and Xu Han and Zhiyuan Liu and Maosong Sun},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2410.10594},
  title = {Vis{RAG}: Vision-based Retrieval-augmented Generation on Multi-modality Documents},
  url = {https://openreview.net/forum?id=zG459X3Xge},
  year = {2025},
}

@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}
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{faysse2024colpali,
  archiveprefix = {arXiv},
  author = {Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and CELINE HUDELOT and Pierre Colombo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.01449},
  title = {ColPali: Efficient Document Retrieval with Vision Language Models},
  url = {https://openreview.net/forum?id=ogjBpZ8uSi},
  year = {2025},
}

@inproceedings{zhou2024vista,
  address = {Bangkok, Thailand},
  author = {Zhou, Junjie and Liu, Zheng and Xiao, Shitao and Zhao, Bo and Xiong, Yongping},
  booktitle = {Proceedings of the 62nd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2024.acl-long.175},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {3185--3200},
  publisher = {Association for Computational Linguistics},
  title = {{VISTA}: Visualized Text Embedding For Universal Multi-Modal Retrieval},
  url = {https://aclanthology.org/2024.acl-long.175/},
  year = {2024},
}

@inproceedings{zhou2024vista,
  address = {Bangkok, Thailand},
  author = {Zhou, Junjie and Liu, Zheng and Xiao, Shitao and Zhao, Bo and Xiong, Yongping},
  booktitle = {Proceedings of the 62nd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2024.acl-long.175},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {3185--3200},
  publisher = {Association for Computational Linguistics},
  title = {{VISTA}: Visualized Text Embedding For Universal Multi-Modal Retrieval},
  url = {https://aclanthology.org/2024.acl-long.175/},
  year = {2024},
}

@inproceedings{zhu2024languagebind,
  archiveprefix = {arXiv},
  author = {Bin Zhu and Bin Lin and Munan Ning and Yang Yan and Jiaxi Cui and WANG HongFa and Yatian Pang and Wenhao Jiang and Junwu Zhang and Zongwei Li and Cai Wan Zhang and Zhifeng Li and Wei Liu and Li Yuan},
  booktitle = {The Twelfth International Conference on Learning Representations},
  eprint = {2310.01852},
  title = {LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment},
  url = {https://openreview.net/forum?id=QmZKc7UZCy},
  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}
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}

@inproceedings{https://doi.org/10.48550/arxiv.2201.12086,
  archiveprefix = {arXiv},
  author = {Junnan Li and Dongxu Li and Caiming Xiong and Steven C. H. Hoi},
  booktitle = {ICML},
  eprint = {2201.12086},
  pages = {12888-12900},
  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  url = {https://proceedings.mlr.press/v162/li22n.html},
  year = {2022},
}