@article{sampleawareadaptivestructuredpruningfor, title = {Sample-aware Adaptive Structured Pruning for Large Language Models}, author = {Jun Kong and Xinge Ma and Jin Wang and Xuejie Zhang}, year = {2025}, eprint = {2503.06184}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.06184v1}, }