@inproceedings{wang-etal-2026-meur,
title = "{MEUR}: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning",
author = "Wang, Zimu and
Wang, Yuqi and
Chen, Tong and
Zeng, Changyu and
Na, Hongbin and
Han, Nijia and
Xing, Fuyu and
Chen, Qi and
Wang, Qiufeng and
Nguyen, Anh and
Wang, Shuihua and
Chen, Ling and
Su, Jionglong and
Zhang, Haiyang and
Wang, Wei",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.134/",
doi = "10.63317/4ftadqtyt374",
pages = "1696--1709",
abstract = "Event understanding and reasoning play critical roles in thoroughly evaluating the capabilities of Vision-Language Models (VLMs); however, existing Visual Question Answering (VQA) datasets predominantly focus on entity-centric questions, while event- or action-related questions are limited in scale and suffer from significant shortcut issues. We introduce MEUR, the first Multimodal Event Understanding and Reasoning dataset consisting of 1,200 images and 4,217 questions, necessitating VLMs with a diverse range of multimodal understanding and reasoning capabilities to answer, ranging from basic event recognition to more complex tasks such as counting and comparison. To streamline the annotation process, we propose a novel semi-automated pipeline that combines advanced VLMs with human annotators, achieving high quality and efficiency. We conduct extensive experiments on state-of-the-art non-thinking and thinking VLMs to demonstrate their capabilities and limitations in multimodal event understanding and reasoning. Furthermore, we provide a detailed error analysis that points out promising directions for future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-meur">
<titleInfo>
<title>MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changyu</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nijia</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuyu</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiufeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuihua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jionglong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event understanding and reasoning play critical roles in thoroughly evaluating the capabilities of Vision-Language Models (VLMs); however, existing Visual Question Answering (VQA) datasets predominantly focus on entity-centric questions, while event- or action-related questions are limited in scale and suffer from significant shortcut issues. We introduce MEUR, the first Multimodal Event Understanding and Reasoning dataset consisting of 1,200 images and 4,217 questions, necessitating VLMs with a diverse range of multimodal understanding and reasoning capabilities to answer, ranging from basic event recognition to more complex tasks such as counting and comparison. To streamline the annotation process, we propose a novel semi-automated pipeline that combines advanced VLMs with human annotators, achieving high quality and efficiency. We conduct extensive experiments on state-of-the-art non-thinking and thinking VLMs to demonstrate their capabilities and limitations in multimodal event understanding and reasoning. Furthermore, we provide a detailed error analysis that points out promising directions for future research.</abstract>
<identifier type="citekey">wang-etal-2026-meur</identifier>
<identifier type="doi">10.63317/4ftadqtyt374</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.134/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1696</start>
<end>1709</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning
%A Wang, Zimu
%A Wang, Yuqi
%A Chen, Tong
%A Zeng, Changyu
%A Na, Hongbin
%A Han, Nijia
%A Xing, Fuyu
%A Chen, Qi
%A Wang, Qiufeng
%A Nguyen, Anh
%A Wang, Shuihua
%A Chen, Ling
%A Su, Jionglong
%A Zhang, Haiyang
%A Wang, Wei
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F wang-etal-2026-meur
%X Event understanding and reasoning play critical roles in thoroughly evaluating the capabilities of Vision-Language Models (VLMs); however, existing Visual Question Answering (VQA) datasets predominantly focus on entity-centric questions, while event- or action-related questions are limited in scale and suffer from significant shortcut issues. We introduce MEUR, the first Multimodal Event Understanding and Reasoning dataset consisting of 1,200 images and 4,217 questions, necessitating VLMs with a diverse range of multimodal understanding and reasoning capabilities to answer, ranging from basic event recognition to more complex tasks such as counting and comparison. To streamline the annotation process, we propose a novel semi-automated pipeline that combines advanced VLMs with human annotators, achieving high quality and efficiency. We conduct extensive experiments on state-of-the-art non-thinking and thinking VLMs to demonstrate their capabilities and limitations in multimodal event understanding and reasoning. Furthermore, we provide a detailed error analysis that points out promising directions for future research.
%R 10.63317/4ftadqtyt374
%U https://aclanthology.org/2026.lrec-1.134/
%U https://doi.org/10.63317/4ftadqtyt374
%P 1696-1709
Markdown (Informal)
[MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning](https://aclanthology.org/2026.lrec-1.134/) (Wang et al., LREC 2026)
ACL
- Zimu Wang, Yuqi Wang, Tong Chen, Changyu Zeng, Hongbin Na, Nijia Han, Fuyu Xing, Qi Chen, Qiufeng Wang, Anh Nguyen, Shuihua Wang, Ling Chen, Jionglong Su, Haiyang Zhang, and Wei Wang. 2026. MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1696–1709, Palma de Mallorca, Spain. ELRA Language Resource Association.