PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models
This work proposes PW-Pruning, a phase-aware extension of DO-ACP that constructs separate importance-weighted kernels for acoustic-prefill and teacher-forced answer tokens, then combines phase-weighted log-determinant marginal gains to select one static expert bank.
Jun-Jie Cao, Feng-Ping Tian, Wen-Jie Zhou et al.
· 0 citations