| title | BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling |
|---|---|
| authors | Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez, Lukas Galke Poech, Peter Schneider-Kamp |
| date | 2026-06-08 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.09707 |
| affiliation | University of Southern Denmark (SDU) |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging. Researchers often need to alter model weights for layer restructuring, precision casting, low-rank factorization, and architectural debugging, yet these workflows often rely on fragile ad-hoc Python scripts. Here, we introduce BrainSurgery, a tool for robust and reproducible "tensor surgery" on neural network checkpoints, and provide a system demonstration covering four examples and three case studies from model upcycling to LoRA extraction. By abstracting storage formats and memory management, BrainSurgery executes complex transformations through declarative YAML plans. It supports structural modifications, mathematical transformations, and tensor reshaping through expressive regex and structural targeting, while built-in assertions validate tensor shapes, data types, and values to prevent silent errors. We envision that BrainSurgery will provide a strong foundation for future research through its reproducible and validated operations. |
cite
@misc{barmina2026brainsurgery,
title={BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling},
author={Gianluca Barmina and Annemette Broch Pirchert and Andrea Blasi Núñez and Lukas Galke Poech and Peter Schneider-Kamp},
year={2026},
eprint={2606.09707},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.09707}
}