LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray

ArXi:2603.19451v1 Announce Type: cross Fine-grained representation learning is crucial for retrieval and phrase grounding in chest X-rays, where clinically relevant findings are often spatially confined. However, the lack of region-level supervision in contrastive models and the limited ability of large vision language models to capture fine-grained representations in external validation lead to suboptimal performance on these tasks.