RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture

ArXi:2601.15891v2 Announce Type: replace Recent advances in medical vision language models guide the learning of visual representations; however, this form of supervision is constrained by the availability of paired image text data, raising the question of whether robust radiology encoders can be learned without relying on language supervision. In this work, we