@inproceedings{kim-etal-2026-spatial,
title = "Spatial Reasoning in Large Vision-Language Models via Egocentric-to-Allocentric Transformation",
author = "Kim, Yoonji and
Kim, Jieun and
Cho, Sung-Bae",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1782/",
doi = "10.18653/2026.findings-emnlp.1782",
pages = "38100--38118",
ISBN = "979-8-89176-462-0",
abstract = "Multi-view spatial reasoning in large vision-language models involves inferring view-specific spatial relations and integrating them into a consistent scene-centered representation. However, existing approaches often learn view-dependent relations tied to individual camera frames, which limits their ability to form viewpoint-invariant spatial representations. Motivated by cognitive models of spatial perspective-taking, we propose \textbf{SCoRE} (Spatial Consistency Reasoning), a method that formulates multi-view spatial reasoning as an egocentric-to-allocentric transformation problem. SCoRE first trains the model to infer egocentric object relations from single-view observations. It then applies reinforcement learning to encourage the model to estimate viewpoint orientation, transform egocentric relations into a shared scene-centered reference frame, and predict allocentric object relations. To enforce viewpoint-invariant reasoning, we optimize the model with a multi-view consistency reward that aligns predictions from different views in the common allocentric space. Experiments show that SCoRE improves spatial reasoning performance by +3.69{\%}p on multi-view benchmarks and +4.72{\%}p on general spatial reasoning benchmarks over prior state-of-the-art methods, demonstrating the effectiveness of explicit reference-frame transformation for robust multi-view spatial understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-spatial">
<titleInfo>
<title>Spatial Reasoning in Large Vision-Language Models via Egocentric-to-Allocentric Transformation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoonji</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sung-Bae</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multi-view spatial reasoning in large vision-language models involves inferring view-specific spatial relations and integrating them into a consistent scene-centered representation. However, existing approaches often learn view-dependent relations tied to individual camera frames, which limits their ability to form viewpoint-invariant spatial representations. Motivated by cognitive models of spatial perspective-taking, we propose SCoRE (Spatial Consistency Reasoning), a method that formulates multi-view spatial reasoning as an egocentric-to-allocentric transformation problem. SCoRE first trains the model to infer egocentric object relations from single-view observations. It then applies reinforcement learning to encourage the model to estimate viewpoint orientation, transform egocentric relations into a shared scene-centered reference frame, and predict allocentric object relations. To enforce viewpoint-invariant reasoning, we optimize the model with a multi-view consistency reward that aligns predictions from different views in the common allocentric space. Experiments show that SCoRE improves spatial reasoning performance by +3.69%p on multi-view benchmarks and +4.72%p on general spatial reasoning benchmarks over prior state-of-the-art methods, demonstrating the effectiveness of explicit reference-frame transformation for robust multi-view spatial understanding.</abstract>
<identifier type="citekey">kim-etal-2026-spatial</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1782</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1782/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>38100</start>
<end>38118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spatial Reasoning in Large Vision-Language Models via Egocentric-to-Allocentric Transformation
%A Kim, Yoonji
%A Kim, Jieun
%A Cho, Sung-Bae
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kim-etal-2026-spatial
%X Multi-view spatial reasoning in large vision-language models involves inferring view-specific spatial relations and integrating them into a consistent scene-centered representation. However, existing approaches often learn view-dependent relations tied to individual camera frames, which limits their ability to form viewpoint-invariant spatial representations. Motivated by cognitive models of spatial perspective-taking, we propose SCoRE (Spatial Consistency Reasoning), a method that formulates multi-view spatial reasoning as an egocentric-to-allocentric transformation problem. SCoRE first trains the model to infer egocentric object relations from single-view observations. It then applies reinforcement learning to encourage the model to estimate viewpoint orientation, transform egocentric relations into a shared scene-centered reference frame, and predict allocentric object relations. To enforce viewpoint-invariant reasoning, we optimize the model with a multi-view consistency reward that aligns predictions from different views in the common allocentric space. Experiments show that SCoRE improves spatial reasoning performance by +3.69%p on multi-view benchmarks and +4.72%p on general spatial reasoning benchmarks over prior state-of-the-art methods, demonstrating the effectiveness of explicit reference-frame transformation for robust multi-view spatial understanding.
%R 10.18653/2026.findings-emnlp.1782
%U https://aclanthology.org/2026.findings-emnlp.1782/
%U https://doi.org/10.18653/2026.findings-emnlp.1782
%P 38100-38118
Markdown (Informal)
[Spatial Reasoning in Large Vision-Language Models via Egocentric-to-Allocentric Transformation](https://aclanthology.org/2026.findings-emnlp.1782/) (Kim et al., Findings 2026)
ACL