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

Vision-Language Memory for Spatial Reasoning

About

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a semantic-geometric misalignment that prevents consistent 3D understanding, and the absence of persistent memory to retain 3D representation and understanding over time. To address these limitations, we present VLM$^2$, a Vision-Language Model with persistent Memory for spatial reasoning with a view-consistent, 3D-aware representation purely from 2D video. Specifically, to enhance long-horizon reasoning, we incorporate a dual-memory module, consisting of a working memory that operates as a sliding window to focus on immediate context, and an episodic memory that consolidates and stores critical long-term information. This design enables efficient and long-horizon spatial reasoning with a fixed computational cost. Extensive experiments on multiple benchmarks show that VLM$^2$ achieves state-of-the-art performance among video-only models, significantly advancing the frontier of visual-spatial intelligence.

Zuntao Liu, Yi Du, Taimeng Fu, Shaoshu Su, Cherie Ho, Chen Wang• 2025

Related benchmarks

TaskDatasetResultRank
Spatial ReasoningVSI-Bench
Avg Score68.8
255
Spatial ReasoningVSTI-Bench
Cam. Mov. Dir. Error76.8
30
Spatial VQASQA3D (test)
Overall Accuracy46.5
22
Showing 3 of 3 rows

Other info

Follow for update