← Search

Xueyan Zhang

2 accepted papers

2025

Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning

EMNLP 2025

In this work, we propose FoRA-UA, a novel method that, using only 1–5% of the standard LoRA’s parameters, achieves state-of-the-art performance across a wide range of tasks. Specifically, we explore scenarios with extremely limited parameter budgets and derive two key insights: (1) fix-sized sparse

Cited by 0SourcePDFScholar
2025

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models

ACL 2025long

This paper introduces UoRA, a novel parameter-efficient fine-tuning (PEFT) approach for large language models (LLMs). UoRA achieves state-of-the-art efficiency by leveraging a low-rank approximation method that reduces the number of trainable parameters without compromising performance. Unlike exist…

Cited by 0SourcePDFScholar