2 papers
cs.CL2025
DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models
Zeping Min, Xinshang Wang
We introduce a novel index, the Distribution of Cosine Similarity (DOCS), for quantitatively assessing the similarity between weight matrices in Large Language Models (LLMs), aimin…
cs.LG2024
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
Mingze Wang, Zeping Min, Lei Wu
In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the spec…