AI RESEARCH
Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts
arXiv CS.CV
•
ArXi:2604.01915v1 Announce Type: new Medical Visual Grounding (MVG) aims to identify diagnostically relevant phrases from free-text radiology reports and localize their corresponding regions in medical images, providing interpretable visual evidence to clinical decision-making. Although recent Vision-Language Models (VLMs) exhibit promising multimodal reasoning ability, their grounding remains insufficient spatial precision, largely due to a lack of explicit localization priors when relying solely on latent embeddings.