SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.02880 · NeurIPS · 2024

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Ehsan Abbasnejad, Cristian Rodriguez-Opazo, Anton Van Den Hengel, Frederic Zhang, Paul Albert

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2407.02880.json · badge: /api/ran/2407.02880.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
fredzzhang/atlas canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
avg Ran
ran, violated the contract we drafted
fredzzhang/atlas/src/learn_task_addition.py
pointer only (licence: NONE) · get_code("aab9d967b4f428fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fredzzhang/atlas 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.

lp_reg Ran
ran; our contract draft was wrong, not the code
fredzzhang/atlas/src/learn_task_negation.py
pointer only (licence: NONE) · get_code("857a5e75ea1b9b4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fredzzhang/atlas 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.

softmax_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fredzzhang/atlas/src/learn_few_shots.py
pointer only (licence: NONE) · get_code("60e9cb8fea03027c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fredzzhang/atlas 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.

_TaskVector Not yet run
unverified (harvested, no recorded run)
fredzzhang/atlas/src/task_vectors.py
pointer only (licence: NONE) · get_code("993c77fbeceb0a99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fredzzhang/atlas 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. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 later) and 2 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
softmax_entropy 22 other papers
14 dated earlier, 1 the same month, 6 later, 1 undated · 4 only as an assembly brick
2006.10726 (2020-06)
TENT: FULLY TEST-TIME ADAPTATION BY ENTROPY MINIMIZATION
2105.08714 (2021-05)
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
2110.14038 (2021-10)
Robustness of Graph Neural Networks at Scale
and 19 more not named here
avg 1 other paper
1 dated earlier
2310.13590 (2023-10)
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction

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

Pre-trained models produce strong generic representations that can be adapted via fine-tuning on specialised datasets. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning that enables the model to capture these specialised representations. The significance of task vectors is such that simple arithmetic operations on them can be used to combine diverse representations from different domains. This paper builds on these properties of task vectors and aims to answer (1) whether components of task vectors, particularly parameter blocks, exhibit similar characteristics, and (2) how such blocks can be used to enhance knowledge composition and transfer. To this end, we introduce aTLAS, an algorithm that linearly combines parameter blocks with different learned coefficients, resulting in anisotropic scaling at the task vector level. We show that such linear combinations explicitly exploit the low intrinsic dimensionality of pre-trained models, with only a few coefficients being the learnable parameters. Furthermore, composition of parameter blocks enables modular learning that effectively leverages the already learned representations, thereby reducing the dependency on large amounts of data. We demonstrate the effectiveness of our method in task arithmetic, few-shot recognition and test-time adaptation, with supervised or unsupervised objectives. In particular, we show that (1) learned anisotropic scaling allows task vectors to be more disentangled, causing less interference in composition; (2) task vector composition excels with scarce or no labelled data and is less prone to domain shift, thus leading to better generalisability; (3) mixing the most informative parameter blocks across different task vectors prior to training can reduce the memory footprint and improve the flexibility of knowledge transfer. Moreover, we show the potential of aTLAS as a parameter-efficient fine-tuning method, particularly with less data, and demonstrate that it can be easily scaled up for higher performance. * Equal contribution. Listed order was determined by a coin toss. Fred formalised the idea; developed the original codebase; conducted experiments on task arithmetic; and drafted the paper. Paul designed and conducted experiments on few-shot recognition, test-time adaptation, parameter-efficient fine-tuning; investigated numerous properties of task vector compositions; and was crucially involved in every stage of the work.

For agents

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

get_harvested_code_for_paper("2407.02880")
get_code_for_paper("2407.02880")
have("2407.02880")

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

curl https://syntology.ai/api/ran/2407.02880.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.02880.svg)](https://syntology.ai/paper/2407.02880)

Connect an agent — have() is free.