Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual Spatial Tuning

About

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders, which brings extra overhead and usually harms general capabilities. To enhance the spatial ability in general architectures, we introduce Visual Spatial Tuning (VST), a comprehensive framework to cultivate VLMs with human-like visuospatial abilities, from spatial perception to reasoning. We first attempt to enhance spatial perception in VLMs by constructing a large-scale dataset termed VST-P, which comprises 4.1 million samples spanning 19 skills across single views, multiple images, and videos. Then, we present VST-R, a curated dataset with 135K samples that instruct models to reason in space. In particular, we adopt a progressive training pipeline: supervised fine-tuning to build foundational spatial knowledge, followed by reinforcement learning to further improve spatial reasoning abilities. Without the side-effect to general capabilities, the proposed VST consistently achieves state-of-the-art results on several spatial benchmarks, including $34.8\%$ on MMSI-Bench and $61.2\%$ on VSIBench. It turns out that the Vision-Language-Action models can be significantly enhanced with the proposed spatial tuning paradigm, paving the way for more physically grounded AI.

Rui Yang, Ziyu Zhu, Yanwei Li, Jingjia Huang, Shen Yan, Siyuan Zhou, Zhe Liu, Xiangtai Li, Shuangye Li, Wenqian Wang, Yi Lin, Hengshuang Zhao• 2025

Related benchmarks

TaskDatasetResultRank
Optical Character RecognitionOCRBench
Score855
433
Multimodal UnderstandingMMStar
Accuracy63.1
407
Diagram UnderstandingAI2D
Accuracy84.9
317
Spatial ReasoningVSI-Bench
Avg Score61.2
255
Document Visual Question AnsweringDocVQA
Accuracy91.7
203
Spatial ReasoningViewspatial
Accuracy52.8
125
Visual PerceptionMMVP
Accuracy54.7
118
Visual ReasoningBLINK
Accuracy62.1
107
Multi-modal UnderstandingMMBench EN
Accuracy83.3
105
Spatial ReasoningEmbSpatial
Overall Accuracy73.7
103
Showing 10 of 52 rows

Other info

GitHub

Follow for update