Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks Article Swipe

MAKE IMPACT

Shijie Lian , Changti Wu , Laurence T. Yang , Hang Yuan , B. X. Yu , Lei Zhang , Kai Chen · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.24473

Spatial intelligence spans a rich suite of abilities, including visualising and transforming shapes, mentally rotating objects, judging relational positions and containment, and estimating numerosity. However, it still remains a critical unresolved challenge for Multimodal Large Language Models (MLLMs). To fill this gap, we propose to treat Euclidean geometry problem-solving as a surrogate task. Specifically, we meticulously constructed a curated multimodal dataset, called Euclid30K, comprising approximately 30K plane and solid geometry problems. Furthermore, to enable the model to learn and apply Euclidean principles from these geometry problems, we fine-tuned seven model variants (spanning 3--72B parameters) from the Qwen2.5VL, Qwen3VL, and RoboBrain2.0 families using Group Relative Policy Optimization (GRPO), inspiring the models to identify shapes, count, and relate entities, and perform multi-step deductive reasoning using Euclidean principles. Our experiments demonstrate that the resulting models achieve substantial zero-shot gains across four spatial reasoning benchmarks (Super-CLEVR, Omni3DBench, VSI-Bench, and MindCube) without any task-specific adaptations. Notably, after training on the Euclid30K, the mean VSI-Bench accuracy rose from 36.6\% to 41.8\% (+5.2\%), and the mean MindCube accuracy rose from 31.4\% to 38.1\% (+6.7\%). To our knowledge, this is the first systematic study showing that geometry-centric fine-tuning can confer vision-language models with broadly transferable spatial skills. Code and Euclid30K dataset can be found in \href{https://zgca-ai4edu.github.io/Euclids_Gift}{this}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2509.24473

PDF

https://arxiv.org/pdf/2509.24473

OA Status

green

OpenAlex ID

https://openalex.org/W4415336589

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415336589

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2509.24473

Digital Object Identifier

Title

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-09-29

Full publication date if available

Authors

Shijie Lian, Changti Wu, Laurence T. Yang, Hang Yuan, B. X. Yu, Lei Zhang, Kai Chen

List of authors in order

Landing page

https://arxiv.org/abs/2509.24473

Publisher landing page

PDF URL

https://arxiv.org/pdf/2509.24473

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2509.24473

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload