Dong-Hai Zhu

most citedLoRA

^{2}

: Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models

1 citations · 1 across the 1 of their papers we have counts for

collaborators

3 papers

cs.CL2025

Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace

Jia-Chen Zhang, Yu-Jie Xiong, Chun-Ming Xia +2

Large language model (LLM) is considered a milestone towards achieving Artificial General Intelligence (AGI). With its advanced emergent capabilities, it adapt to a wide range of s…

cs.CL2025

Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting

Dong-Hai Zhu, Yu-Jie Xiong, Jia-Chen Zhang +2

Chain-of-Thought (CoT) Prompting is a dominant paradigm in Large Language Models (LLMs) to enhance complex reasoning. It guides LLMs to present multi-step reasoning, rather than ge…

cs.CL2024★ 1 cited

LoRA $^{2}$ : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models

Jia-Chen Zhang, Yu-Jie Xiong, He-Xi Qiu +2

Fine-tuning large language models (LLMs) with high parameter efficiency for downstream tasks has become a new paradigm. Low-Rank Adaptation (LoRA) significantly reduces the number…

Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace

Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting

LoRA2 : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models

LoRA $^{2}$ : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models