@inproceedings{hui-etal-2025-winspot,
title = "{W}in{S}pot: {GUI} Grounding Benchmark with Multimodal Large Language Models",
author = "Hui, Zheng and
Li, Yinheng and
Zhao, Dan and
Banbury, Colby and
Chen, Tianyi and
Koishida, Kazuhito",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.85/",
doi = "10.18653/v1/2025.acl-short.85",
pages = "1086--1096",
ISBN = "979-8-89176-252-7",
abstract = "Graphical User Interface (GUI) automation relies on accurate GUI grounding. However, obtaining large-scale, high-quality labeled data remains a key challenge, particularly in desktop environments like Windows Operating System (OS). Existing datasets primarily focus on structured web-based elements, leaving a gap in real-world GUI interaction data for non-web applications. To address this, we introduce a new framework that leverages LLMs to generate large-scale GUI grounding data, enabling automated and scalable labeling across diverse interfaces. To ensure high accuracy and reliability, we manually validated and refined 5,000 GUI coordinate-instruction pairs, creating WinSpot{---}the first benchmark specifically designed for GUI grounding tasks in Windows environments. WinSpot provides a high-quality dataset for training and evaluating visual GUI agents, establishing a foundation for future research in GUI automation across diverse and unstructured desktop environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hui-etal-2025-winspot">
<titleInfo>
<title>WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colby</namePart>
<namePart type="family">Banbury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuhito</namePart>
<namePart type="family">Koishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-252-7</identifier>
</relatedItem>
<abstract>Graphical User Interface (GUI) automation relies on accurate GUI grounding. However, obtaining large-scale, high-quality labeled data remains a key challenge, particularly in desktop environments like Windows Operating System (OS). Existing datasets primarily focus on structured web-based elements, leaving a gap in real-world GUI interaction data for non-web applications. To address this, we introduce a new framework that leverages LLMs to generate large-scale GUI grounding data, enabling automated and scalable labeling across diverse interfaces. To ensure high accuracy and reliability, we manually validated and refined 5,000 GUI coordinate-instruction pairs, creating WinSpot—the first benchmark specifically designed for GUI grounding tasks in Windows environments. WinSpot provides a high-quality dataset for training and evaluating visual GUI agents, establishing a foundation for future research in GUI automation across diverse and unstructured desktop environments.</abstract>
<identifier type="citekey">hui-etal-2025-winspot</identifier>
<identifier type="doi">10.18653/v1/2025.acl-short.85</identifier>
<location>
<url>https://aclanthology.org/2025.acl-short.85/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1086</start>
<end>1096</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models
%A Hui, Zheng
%A Li, Yinheng
%A Zhao, Dan
%A Banbury, Colby
%A Chen, Tianyi
%A Koishida, Kazuhito
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-252-7
%F hui-etal-2025-winspot
%X Graphical User Interface (GUI) automation relies on accurate GUI grounding. However, obtaining large-scale, high-quality labeled data remains a key challenge, particularly in desktop environments like Windows Operating System (OS). Existing datasets primarily focus on structured web-based elements, leaving a gap in real-world GUI interaction data for non-web applications. To address this, we introduce a new framework that leverages LLMs to generate large-scale GUI grounding data, enabling automated and scalable labeling across diverse interfaces. To ensure high accuracy and reliability, we manually validated and refined 5,000 GUI coordinate-instruction pairs, creating WinSpot—the first benchmark specifically designed for GUI grounding tasks in Windows environments. WinSpot provides a high-quality dataset for training and evaluating visual GUI agents, establishing a foundation for future research in GUI automation across diverse and unstructured desktop environments.
%R 10.18653/v1/2025.acl-short.85
%U https://aclanthology.org/2025.acl-short.85/
%U https://doi.org/10.18653/v1/2025.acl-short.85
%P 1086-1096
Markdown (Informal)
[WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models](https://aclanthology.org/2025.acl-short.85/) (Hui et al., ACL 2025)
ACL
- Zheng Hui, Yinheng Li, Dan Zhao, Colby Banbury, Tianyi Chen, and Kazuhito Koishida. 2025. WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1086–1096, Vienna, Austria. Association for Computational Linguistics.