Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning

ArXi:2605.26292v1 Announce Type: cross Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing methods remain deterministic and often struggle under domain shift or ambiguous image-text alignment. This limitation is particularly critical in the clinic, where models should remain robust in low-data regimes and domain shifts.