paper-with-me

홈 › Papers

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

2025-09-29 · Shijie Lian, Changti Wu, Laurence Tianruo Yang, Hang Yuan, Bin Yu, Lei Zhang, Kai Chen arxiv

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}.

📄 PDF Abstract BibTeX arXiv:2509.24473

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial Reasoning

Similar Papers 제목 키워드 기반

GIFT: Geometry-Informed Low-precision Gradient Communication for LLM Pretraining

2026-07-08 · Jieying Wang, Shuyuan Fan, Mingkai Zheng, Zhao Zhang arxiv

Gradient communication is a primary scaling bottleneck in large language model (LLM) pretraining. Communicating gradients in low-precision formats, such as FP8 and NVFP4, can significantly reduce the communication volume…

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

2025-04-08 · Sanchit Kabra, Akshita Jha, Chandan K. Reddy

Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's abilit…

Fairness

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning

2026-02-07 · Yancheng Long, Yankai Yang, Hongyang Wei, Wei Chen 외 arxiv

Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle wit…

Reinforcement LearningSpatial ReasoningImage Editing

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

2026-04-02 · Yongkang Li, Lijun Zhou, Sixu Yan, Bencheng Liao 외 arxiv

Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of driving systems. However, adapting such models…

Autonomous DrivingMotion Forecasting

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models

2026-05-02 · Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang 외 arxiv

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches …