SOURCE-LINKED INTELLIGENCE

Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Recent 3D foundation models enable generalizable geometric reasoning from RGB images but remain limited in persistent memory, scalability, and renderable scene modeling. We present a memory-centric 3D foundation model for scalable robotic localization, reconstruction, and Gaussian rendering. Its core is an adaptive world memory mechanism that combines transformer-based gated updates with test-time temporal-spatial regulation. Learned gates control recurrent memory propagation, while temporal state evolution and spatial observation-state consistency regulate token-wise updates and forgetting ov

Read original source ↗ Open in workspace

recordType

paper

region

Global