@inproceedings{ridoy-etal-2026-geo,
title = "Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review",
author = "Ridoy, Shahriyar Zaman and
Wasi, Azmine Toushik and
Tonmoy, Koushik Ahamed and
Parvez, Md Rizwan",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.65/",
pages = "1377--1411",
ISBN = "979-8-89176-439-2",
abstract = "Geo-spatial and geo-temporal reasoning require models to determine not only what information is present but also where and when it applies, which is critical for applications such as crisis response, environmental monitoring, and urban planning. This review surveys recent advances in vision{--}language models (VLMs) and large language models (LLMs) that address geographically and temporally grounded reasoning across tasks including image geolocation, spatiotemporal question answering, language-guided navigation, and Earth observation. We organize the literature through a structured analysis covering task families, input modalities, model architectures, and reasoning paradigms, highlighting how perception, retrieval, tool use, and intermediate reasoning steps contribute to system performance. The survey further synthesizes existing datasets and benchmarks, identifying common evaluation pitfalls such as spatial granularity mismatch, temporal drift, geographic bias, and potential data leakage. Finally, we outline key research challenges and opportunities for developing robust, verifiable, and time-aware geo-spatial AI systems while addressing broader concerns related to fairness, bias, and location privacy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ridoy-etal-2026-geo">
<titleInfo>
<title>Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shahriyar</namePart>
<namePart type="given">Zaman</namePart>
<namePart type="family">Ridoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koushik</namePart>
<namePart type="given">Ahamed</namePart>
<namePart type="family">Tonmoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Geo-spatial and geo-temporal reasoning require models to determine not only what information is present but also where and when it applies, which is critical for applications such as crisis response, environmental monitoring, and urban planning. This review surveys recent advances in vision–language models (VLMs) and large language models (LLMs) that address geographically and temporally grounded reasoning across tasks including image geolocation, spatiotemporal question answering, language-guided navigation, and Earth observation. We organize the literature through a structured analysis covering task families, input modalities, model architectures, and reasoning paradigms, highlighting how perception, retrieval, tool use, and intermediate reasoning steps contribute to system performance. The survey further synthesizes existing datasets and benchmarks, identifying common evaluation pitfalls such as spatial granularity mismatch, temporal drift, geographic bias, and potential data leakage. Finally, we outline key research challenges and opportunities for developing robust, verifiable, and time-aware geo-spatial AI systems while addressing broader concerns related to fairness, bias, and location privacy.</abstract>
<identifier type="citekey">ridoy-etal-2026-geo</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.65/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1377</start>
<end>1411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review
%A Ridoy, Shahriyar Zaman
%A Wasi, Azmine Toushik
%A Tonmoy, Koushik Ahamed
%A Parvez, Md Rizwan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F ridoy-etal-2026-geo
%X Geo-spatial and geo-temporal reasoning require models to determine not only what information is present but also where and when it applies, which is critical for applications such as crisis response, environmental monitoring, and urban planning. This review surveys recent advances in vision–language models (VLMs) and large language models (LLMs) that address geographically and temporally grounded reasoning across tasks including image geolocation, spatiotemporal question answering, language-guided navigation, and Earth observation. We organize the literature through a structured analysis covering task families, input modalities, model architectures, and reasoning paradigms, highlighting how perception, retrieval, tool use, and intermediate reasoning steps contribute to system performance. The survey further synthesizes existing datasets and benchmarks, identifying common evaluation pitfalls such as spatial granularity mismatch, temporal drift, geographic bias, and potential data leakage. Finally, we outline key research challenges and opportunities for developing robust, verifiable, and time-aware geo-spatial AI systems while addressing broader concerns related to fairness, bias, and location privacy.
%U https://aclanthology.org/2026.aacl-long.65/
%P 1377-1411
Markdown (Informal)
[Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review](https://aclanthology.org/2026.aacl-long.65/) (Ridoy et al., AACL-IJCNLP 2026)
ACL
- Shahriyar Zaman Ridoy, Azmine Toushik Wasi, Koushik Ahamed Tonmoy, and Md Rizwan Parvez. 2026. Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1377–1411, Hengqin, China. Association for Computational Linguistics.