REC-RL: Referring expression counting via Gaussian and range-based reward optimization

ArXi:2605.16460v1 Announce Type: new Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased reinforcement learning with rewards focused primarily on final accuracy, overlooking the quality of intermediate reasoning. We propose REC-RL, a reinforcement learning framework that