SOURCE-LINKED INTELLIGENCE

GLAM: Training a latent world model over global spatiotemporal memory for active exploration and navigation

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Active exploration and semantic navigation require an embodied agent to build memory from partial observations, predict how the evolution of observed spatial memory may support future motion, and convert that prediction into actionable plans. We present GLAM, a goal-conditioned latent world model trained over global spatiotemporal memory, and GLAM NAV, the complete navigation system built around it. Given historical map tokens, a navigation goal, and the current robot pose, GLAM jointly predicts future map representations and robot-centric waypoint latents, allowing future spatial context and

Read original source ↗ Open in workspace

recordType

paper

region

Global