collaborators

1 paper

cs.IR2026

GAP-Net: Calibrating User Intent via Gated Adaptive Progressive Learning for CTR Prediction

Shenqiang Ke, Jianxiong Wei, Qingsong Hua

Sequential user behavior modeling is pivotal for Click-Through Rate (CTR) prediction yet is hindered by three intrinsic bottlenecks: (1) the "Attention Sink" phenomenon, where stan…