We Should Chart an Atlas of All the World's Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916773609078784 |
|---|---|
| author | Horwitz, Eliahu Kurer, Nitzan Kahana, Jonathan Amar, Liel Hoshen, Yedid |
| author_facet | Horwitz, Eliahu Kurer, Nitzan Kahana, Jonathan Amar, Liel Hoshen, Yedid |
| contents | Public model repositories now contain millions of models, yet most models remain undocumented and effectively lost. In this position paper, we advocate for charting the world's model population in a unified structure we call the Model Atlas: a graph that captures models, their attributes, and the weight transformations that connect them. The Model Atlas enables applications in model forensics, meta-ML research, and model discovery, challenging tasks given today's unstructured model repositories. However, because most models lack documentation, large atlas regions remain uncharted. Addressing this gap motivates new machine learning methods that treat models themselves as data, inferring properties such as functionality, performance, and lineage directly from their weights. We argue that a scalable path forward is to bypass the unique parameter symmetries that plague model weights. Charting all the world's models will require a community effort, and we hope its broad utility will rally researchers toward this goal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10633 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | We Should Chart an Atlas of All the World's Models Horwitz, Eliahu Kurer, Nitzan Kahana, Jonathan Amar, Liel Hoshen, Yedid Machine Learning Computation and Language Computer Vision and Pattern Recognition Public model repositories now contain millions of models, yet most models remain undocumented and effectively lost. In this position paper, we advocate for charting the world's model population in a unified structure we call the Model Atlas: a graph that captures models, their attributes, and the weight transformations that connect them. The Model Atlas enables applications in model forensics, meta-ML research, and model discovery, challenging tasks given today's unstructured model repositories. However, because most models lack documentation, large atlas regions remain uncharted. Addressing this gap motivates new machine learning methods that treat models themselves as data, inferring properties such as functionality, performance, and lineage directly from their weights. We argue that a scalable path forward is to bypass the unique parameter symmetries that plague model weights. Charting all the world's models will require a community effort, and we hope its broad utility will rally researchers toward this goal. |
| title | We Should Chart an Atlas of All the World's Models |
| topic | Machine Learning Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.10633 |