Papers by Rongguang Ye

1 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations