Papers by Rongguang Ye
One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing pruning methods for large language models (LLMs) focus on achieving high compression rates while maintaining model performance. |
| Approach: | They propose a Univeral Model for Customized Compression (UniCuCo) which introduces a StratNet that learns to map arbitrary requests to their optimal pruning strategy. |
| Outcome: | The proposed model is 28 times faster than baselines in processing 64 requests, while maintaining comparable accuracy to baselines. |