Yongmin Kim

Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model

A training-free adaptive pruning method designed specifically for batched inference in LRMs, built on two components: periodic top-k selection over the aggregated importance scores, unaffected by the shift that aggregation induces in the activation distribution, and based on the observation that important neurons re-fi...