Article

HGWM: Zero-Shot Object Navigation Using Hierarchical Graph-Guided World Models and Graph Matching

The authors propose HGWM, which combines an LLM-generated room-anchor prior with persistent spatial-semantic memory to select search directions in zero-shot object navigation. On HM3D v0.1, it reports 62.6% success rate and 31.5% SPL, versus 58.1% and 31.2% for WMNav; on MP3D, 46.8% and 17.9%, versus 45.4% and 17.2%.

Part of the event: HGWM: Graph-Guided World Model Achieves Zero-Shot Object Navigation

This page provides a summary and source link only.