Zhihao, Y., Zuxin, M., Guowei, S., Yi, C., Chun, G., Xiaoqi, D., Qing, Q., Yunhe, C. (2026). Layer-wise heterogeneity-guided heterogeneous pruning: An LLM compression method. Journal of King Saud University - Computer and Information Sciences. https://doi.org/10.1007/s44443-026-00724-4