SOURCE-LINKED INTELLIGENCE

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate unseen environments by following natural language instructions. Current zero-shot VLN-CE methods either rely on pre-trained waypoint predictors or require multiple queries to large models per step. To address prohibitive inference latency and computational overhead, we propose O2C-Nav, an efficient zero-shot navigation framework that calls only a single large model once per decision step. Our approach introduces a training-free structured waypoint generator and a novel abstract representat

Read original source ↗ Open in workspace

recordType

paper

region

Global