← Search

REN Lianhai

2 accepted papers

2025

From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control

ICML 2025oral

The LoRA method has achieved notable success in reducing GPU memory usage by applying low-rank updates to weight matrices. Yet, one simple question remains: can we push this reduction even further? Furthermore, is it possible to achieve this while improving performance and reducing computation time?…

Cited by 0SourcePDFScholar