XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation

ArXi:2604.03297v1 Announce Type: cross In the field of Large Language Models (LLMs), Attention Residuals have recently nstrated that learned, selective aggregation over all preceding layer outputs can outperform fixed residual connections. We propose Cross-Stage Attention Residuals (XAttnRes), a mechanism that maintains a global feature history pool accumulating both encoder and decoder stage outputs. Through lightweight pseudo-query attention, each stage selectively aggregates from all preceding representations.