Author ORCID Identifier

https://orcid.org/0009-0005-2310-2581

Date of Award

Spring 6-3-2026

Document Type

Thesis (Undergraduate)

Department

Computer Science

First Advisor

Yaoqing Yang

Abstract

With the rapid development of open-sourced models on Huggingface, there is a strong need for a way to systematically determine the similarity between models. More strongly, for intellectual property and organization, we need a way to determine the "lineage" of models. We borrow principles from Heavy-Tailed Self-Regularization and Random Matrix Theory to provide an inference-free method to accomplish this. We cluster a corpus of several model families by their spectral fingerprints and demonstrate that each model family occupies a distinct region in weight space. This confirms prior ideas of training setups leaving artifacts on model weights and allows us to formally capture intrinsic similarities embedded into model structures.

Share

COinS