CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation

ArXi:2510.11173v3 Announce Type: replace Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)-based positional perception model that bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap.