Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial intelligence. The core challenge is not simply longer context windows but how spatial information is selected, organized, and retained over time. In this paper, we propose Spatial-TTT towards streaming visual-based spatial intelligence with test-time training (TTT), which adapts a subset of parameters (fast weights) to capture and organize spatial evidence over long-horizon scene videos. Specifically, we design a hybrid architecture and adopt large-chunk updates...
| Authors | Fangfu Liu, Diankun Wu, Jiawei Chi et al. |
|---|---|
| Primary category | cs.CV |
| Published | 12 March 2026 |
| Last updated at source | 12 March 2026 |
Connected in the knowledge graph
- Wuuu3511/TraingTangTianDataset · cited by
Models and datasets referencing this paper
- Wuuu3511/TraingTangTianDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.