Preprint
Aug 2026
SeVeR: Selective Visual Exposure and Retrieval for 3D Medical Image Question Answering
SeVeR is proposed, a selective visual exposure framework that compresses dense volumes into modality-wise prototypes and retrieves complementary multi-level evidence with change-aware gated attention during decoding, trained with a marginal-utility self-consistency objective that suppresses unhelpful retrieval.
Yao-Jun Hu, Danyang Tu, Yang Liu et al.
· 0 citations