Skip to content

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

Sep 2026 · arXiv.org · Vol abs/2609.14561 · 0 citations · 29 references
Computer Science

TL;DR

GLAM, a goal-conditioned latent world model trained over global spatiotemporal memory, and GLAM NAV, the complete navigation system built around it are presented, allowing future spatial context and navigation intent to be inferred in a shared representation space.

Abstract

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 navigation intent to be inferred in a shared representation space. The model follows a JEPA-like latent prediction paradigm, operates directly on map-level latent tokens rather than RGB reconstruction, and uses a pretrained waypoint encoder-decoder to supervise and decode navigation plans within GLAM NAV. Training data are collected by replaying ObjectNav expert trajectories in Habitat over HM3D v0.2 scene assets and slicing them into multi-timescale prediction samples. On a controlled HM3D-ObjectNav subset reproduction setting, GLAM NAV improves over a reproduced BSC-Nav baseline in both success rate and success weighted by path length.

View source

Similar papers

#artificial intelligence Preprint Nov 2026

OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining

Navigation world models predict future observations conditioned on navigation actions to support planning, but their generalization across real-world environments remains constrained by the limited coverage of action-labeled data. Action-free navigation videos provide diverse visual experience, yet lack the recorded ac...

Du-Jun Nie, Rui-Qi Song, Zi-Xuan Wang et al. · 0 citations
Preprint Oct 2026

LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild

Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation world models provide this foresight through visual rollouts, which are costly when evaluating multiple candidates. We present LiteNWM, a latent navigation world model that...

Lin-Kai Liu, Yun-Tian Zhang, Zhen-Shan Bing et al. · 0 citations
Preprint Oct 2026

Beyond Action Prediction: Learning Search-Free Planning in Latent Space

Latent world models learn action-conditioned state transitions in a compact representation space, providing a predictive model for visual planning and control. However, planning with these models typically requires costly test-time optimization over action sequences. We propose to replace this online search with a goal...

Guan-Chen Du, Jin-Hao Du, Yan-Peng Sun et al. · 0 citations
Sep 2026

InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning

Language-guided navigation requires connecting partial observations to a persistent spatial reference and learning how actions change that representation. We introduce InsightMap, a framework that uses top-down maps as both explicit spatial memory and action-conditioned prediction targets. Historical views are linked t...

Hong-Pei Zheng, Hu-Jun Yin · 0 citations
Preprint Oct 2026

MemWM: Associative Memory-Enhanced Latent World Models for Long-Horizon Planning

World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon capability. We introduce Memory World Model (MemWM), an associative memory-enhanced latent world model that augments JEPA-sty...

Yu-Wei Sun, Si-Yu Zhu · 0 citations

Scope-WM: Scoped Computation for Efficient Visual World Models

Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimization incur high inference latency and peak memory usage, limiting real-time deployment on resource-constrained platforms. Existing sparse world-model acceleration met...

Chun-Zheng Li, Ze-Sheng Jia, Hong-Da Zhang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.