Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection

ArXi:2603.24166v1 Announce Type: new Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face severe label scarcity. In such regimes, end-to-end grounding detectors need to learn spatial and semantic structure from scratch, wasting precious samples. We ask a simple question: Can explicit reasoning priors help models learn efficiently when data is scarce? To explore this, we first.