Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation

ArXi:2603.09506v1 Announce Type: new Text-goal instance navigation (TGIN) asks an agent to resolve a single, free-form description into actions that reach the correct object instance among same-category distractors. We present \textit{Context-Na} that elevates long, contextual captions from a local matching cue to a global exploration prior and verifies candidates through 3D spatial reasoning. First, we compute dense text-image alignments for a value map that ranks frontiers -- guiding exploration toward regions consistent with the entire description rather than early detections.