PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought (opens in new tab)

Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input images into static feature representations and perform reasoning primarily within the linguistic domain, often overlooking the rich perceptual cues and explicit spatial geometry inherent in images. In this study, we aim to mitigat...