Zhexuan Gu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
PrunePath: Towards Highly Structured Sparse Language Models
PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable speedups.
Highlighted terms show continued research focus across papers