You-Liang Huang

Representation Drift Compensation: A Zero-Cost Enhancement for LLM Decomposition

Efficient Fine-tuning with Decomposed Foundation Model

MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition

Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition

Automatic Truncation Position Selection in Singular Value Decomposition for Large Language Models

NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models