SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2505.22697 · ICML · 2025

Update Your Transformer to the Latest Release: Re-Basin of Task Vectors

Angelo Porrello, Simone Calderara, Emanuele Rodolà, Lorenzo Bonicelli, Elisa Ficarra, Donato Crisostomi, Filippo Rinaldi, Giacomo Capitani, Federico Bolelli

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 3 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2505.22697.json · badge: /api/ran/2505.22697.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
aimagelab/transfusion canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
4 ran · 0 no recorded run
FunctionStatusWhere it lives
TaskVector Ran
ran on a synthesized input · constructed an object; no result was computed
aimagelab/transfusion/task_vectors/src/task_vectors.py
pointer only (licence: NONE) · get_code("b0db24cb0bcb77f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aimagelab/transfusion when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

default Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/gradnorm-pytorch
pointer only · get_code("99b3563ebc6734ad")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

divisible_by Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/soft-moe-pytorch
pointer only · get_code("f912c209e9c899ca")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exists Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/gradnorm-pytorch
pointer only · get_code("b7c3487f192e31b7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

identity Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/memorizing-transformers-pytorch
pointer only · get_code("f3232418205f7cbd")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
exists 27 other papers
21 dated earlier, 6 later · 3 only as an assembly brick
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
2006.15055 (2020-06)
Object-Centric Learning with Slot Attention
2010.10241 (2020-10)
BYOL works even without batch statistics
and 24 more not named here
default 21 other papers
18 dated earlier, 3 later · 1 only as an assembly brick
2006.15055 (2020-06)
Object-Centric Learning with Slot Attention
2110.00218 (2021-10)
On the Importance of Gradients for Detecting Distributional Shifts in the Wild
2309.02612 (2023-09)
Music Source Separation with Band-Split RoPE Transformer
and 18 more not named here
identity 21 other papers
16 dated earlier, 4 later, 1 undated · 2 only as an assembly brick
2011.10043 (2020-11)
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
2203.08913 (2022-03)
Memorizing Transformers
2302.04761 (2023-02)
Toolformer: Language Models Can Teach Themselves to Use Tools
and 18 more not named here
divisible_by 16 other papers
13 dated earlier, 3 later · 2 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2010.10241 (2020-10)
BYOL works even without batch statistics
2102.06810 (2021-02)
Understanding self-supervised Learning Dynamics without Contrastive Pairs
and 13 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model becomes obsolete, losing its utility and requiring retraining. This raises the question: is it possible to transfer fine-tuning to a new release of the model? In this work, we investigate how to transfer fine-tuning to a new checkpoint without having to re-train, in a data-free manner. To do so, we draw principles from model re-basin and provide a recipe based on weight permutations to re-base the modifications made to the original base model, often called task vector. In particular, our approach tailors model re-basin for Transformer models, taking into account the challenges of residual connections and multi-head attention layers. Specifically, we propose a twolevel method rooted in spectral theory, initially permuting the attention heads and subsequently adjusting parameters within select pairs of heads. Through extensive experiments on visual and textual tasks, we achieve the seamless transfer of fine-tuned knowledge to new pre-trained backbones without relying on a single training step or datapoint. Code is available at https:// github.com/aimagelab/TransFusion.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2505.22697")
get_code_for_paper("2505.22697")
have("2505.22697")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2505.22697.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2505.22697.svg)](https://syntology.ai/paper/2505.22697)

Connect an agent — have() is free.