Abstract
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical memory. However, as memory sequences grow longer and their structures become increasingly complex, managing long-range spatial context becomes increasingly challenging, calling for a more intelligent and systematic memory-management strategy. Building on the advancing spatial reasoning capabilities of multimodal large language models (MLLMs) and the broader vision of unified models, we propose Spatial Memory Intelligence (SMI), the first framework to systematically employ an understanding model for spatial-memory management in long-video world models. SMI introduces four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering. Extensive experiments across multiple baselines, benchmarks, and world-model backbones demonstrate the effectiveness and generalizability of SMI, achieving comprehensive improvements in memory sparsity, generation stability, and spatial consistency.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yang, Y., Zhang, G., Huang, L., Nie, C., Si, C., Wang, H., Shi, S., & Jiang, L. (2026). Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory. https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory
MLA 9
Yang, Ying, et al. "Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory." https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory.
Chicago (author–date)
Yang, Ying, Guiyu Zhang, Lianghua Huang, Chang Nie, Chenyang Si, Haofan Wang, Shaoshuai Shi, and Li Jiang. 2026. "Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory." https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory.
Harvard
Yang, Y., Zhang, G., Huang, L., Nie, C., Si, C., Wang, H., Shi, S. and Jiang, L. (2026) 'Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory', Available at: https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory.
Vancouver
Yang Y, Zhang G, Huang L, Nie C, Si C, Wang H, et al. Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory. https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory
IEEE
Y. Yang, G. Zhang, L. Huang, C. Nie, C. Si, H. Wang, S. Shi, and L. Jiang, "Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory," https://omanscience.com/en/articles/spatial-memory-intelligence-endowing-world-models-with-understanding-driven-long-term-memory.