@inproceedings{gunther-etal-2025-jina,
title = "jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval",
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},
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",
booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
month = nov,
year = "2025",
address = "Suzhuo, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mrl-main.36/",
doi = "10.18653/v1/2025.mrl-main.36",
pages = "531--550",
ISBN = "979-8-89176-345-6",
abstract = "We introduce jina-embeddings-v4, a 3.8 billion parameter embedding model that unifies text and image representations, with a novel architecture supporting both single-vector and multi-vector embeddings. It achieves high performance on both single-modal and cross-modal retrieval tasks, and is particularly strong in processing visually rich content such as tables, charts, diagrams, and mixed-media formats that incorporate both image and textual information. We also introduce JVDR, a novel benchmark for visually rich document retrieval that includes more diverse materials and query types than previous efforts. We use JVDR to show that jina-embeddings-v4 greatly improves on state-of-the-art performance for these kinds of tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gunther-etal-2025-jina">
<titleInfo>
<title>jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Günther</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Sturua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Kalim</namePart>
<namePart type="family">Akram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Mohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Ungureanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sedigheh</namePart>
<namePart type="family">Eslami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Martens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Werk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Raja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhuo, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-345-6</identifier>
</relatedItem>
<abstract>We introduce jina-embeddings-v4, a 3.8 billion parameter embedding model that unifies text and image representations, with a novel architecture supporting both single-vector and multi-vector embeddings. It achieves high performance on both single-modal and cross-modal retrieval tasks, and is particularly strong in processing visually rich content such as tables, charts, diagrams, and mixed-media formats that incorporate both image and textual information. We also introduce JVDR, a novel benchmark for visually rich document retrieval that includes more diverse materials and query types than previous efforts. We use JVDR to show that jina-embeddings-v4 greatly improves on state-of-the-art performance for these kinds of tasks.</abstract>
<identifier type="citekey">gunther-etal-2025-jina</identifier>
<identifier type="doi">10.18653/v1/2025.mrl-main.36</identifier>
<location>
<url>https://aclanthology.org/2025.mrl-main.36/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>531</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
%A Günther, Michael
%A Sturua, Saba
%A Akram, Mohammad Kalim
%A Mohr, Isabelle
%A Ungureanu, Andrei
%A Wang, Bo
%A Eslami, Sedigheh
%A Martens, Scott
%A Werk, Maximilian
%A Wang, Nan
%A Xiao, Han
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F gunther-etal-2025-jina
%X We introduce jina-embeddings-v4, a 3.8 billion parameter embedding model that unifies text and image representations, with a novel architecture supporting both single-vector and multi-vector embeddings. It achieves high performance on both single-modal and cross-modal retrieval tasks, and is particularly strong in processing visually rich content such as tables, charts, diagrams, and mixed-media formats that incorporate both image and textual information. We also introduce JVDR, a novel benchmark for visually rich document retrieval that includes more diverse materials and query types than previous efforts. We use JVDR to show that jina-embeddings-v4 greatly improves on state-of-the-art performance for these kinds of tasks.
%R 10.18653/v1/2025.mrl-main.36
%U https://aclanthology.org/2025.mrl-main.36/
%U https://doi.org/10.18653/v1/2025.mrl-main.36
%P 531-550
Markdown (Informal)
[jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval](https://aclanthology.org/2025.mrl-main.36/) (Günther et al., MRL 2025)
ACL
- Michael Günther, Saba Sturua, Mohammad Kalim Akram, Isabelle Mohr, Andrei Ungureanu, Bo Wang, Sedigheh Eslami, Scott Martens, Maximilian Werk, Nan Wang, and Han Xiao. 2025. jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval. In Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pages 531–550, Suzhuo, China. Association for Computational Linguistics.