Story
arxiv_cs_ai · Sep 6, 2026 · paper
Source brief
One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints
arxiv.orgSep 6, 2026
original source linked
In brief
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...
Feed lens
agentevaluation