Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.20644 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914170974240768 |
|---|---|
| author | Liu, Zuntao Du, Yi Fu, Taimeng Su, Shaoshu Ho, Cherie Wang, Chen |
| author_facet | Liu, Zuntao Du, Yi Fu, Taimeng Su, Shaoshu Ho, Cherie Wang, Chen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20644 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vision-Language Memory for Spatial Reasoning Liu, Zuntao Du, Yi Fu, Taimeng Su, Shaoshu Ho, Cherie Wang, Chen Computer Vision and Pattern Recognition 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. |
| title | Vision-Language Memory for Spatial Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.20644 |