SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15017 · ICLR · 2024

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Fangzhou Mu, Yingyu Liang, Yin Li, Zhenmei Shi, Junyi Wei, Zhuoyan Xu

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 failures of our instrument; 8 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/2402.15017.json · badge: /api/ran/2402.15017.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
OliverXUZY/Foudation-Model_Multitask canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
oliverxuzy/foudation-model_multitask alias (classifier label)
classifier basis: classifier_2025
7 ran · 7 no recorded run
FunctionStatusWhere it lives
AverageMeter Ran
ran on a synthesized input · constructed an object; no result was computed
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("448391a260518c64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

Timer Ran
ran on a synthesized input · constructed an object; no result was computed
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("103e5bf76abe5b7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

count_params Ran
ran; our contract draft was wrong, not the code
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("57935c9233ae310a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

decay_lr Ran
ran, honoured the contract we drafted
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("05f178cf8f67fb2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

make Ran
ran; our contract draft was wrong, not the code
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("5c0a845766c67c36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

register Ran
ran; our contract draft was wrong, not the code
OliverXUZY/Foudation-Model_Multitask/datasets/datasets.py
pointer only (licence: NONE); the stored copy get_code serves, from daidaijr/EAMamba, is pointer only (licence: NONE) · get_code("9687bf7a922f098a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OliverXUZY/Foudation-Model_Multitask 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.

time_str Ran
ran; our contract draft was wrong, not the code
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("df8ef801f1f069b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

warmup Ran
ran, honoured the contract we drafted
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("b5536ea9ed2c47b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

accuracy Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("3a86045f15981b84")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

ensure_path Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("34e85ca54daccd74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

log Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("7d408a58c39fd05b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

main Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("19ca843d619cc77a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

make Not yet run
unverified (harvested, no recorded run)
OliverXUZY/Foudation-Model_Multitask/datasets/datasets.py
pointer only (licence: NONE) · get_code("db58e5a4a5aafdab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OliverXUZY/Foudation-Model_Multitask 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.

make_path Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("94b1635e5243cca8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

set_bn_eval Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("08a4ae2c29e737a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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.

set_log_path Not yet run
unverified (harvested, no recorded run)
oliverxuzy/foudation-model_multitask/finetune.py
pointer only (licence: NONE) · get_code("f4bfac480be197ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverxuzy/foudation-model_multitask 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 14 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
register 5 other papers
4 dated earlier, 1 later
2111.08918 (2021-11)
Local Texture Estimator for Implicit Representation Function
Pak_B-Spline_Texture_Coefficients_Estimator_for_Screen_Content_Image_Super-Resolution_CVPR_2023_paper (2023 (year only))
B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution
2310.10207 (2023-10)
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
and 2 more not named here
time_str
brick of this paper's assembly: helper
1 other paper
1 later
2405.03649 (2024-05)
Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation

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 have emerged as a powerful tool for many AI problems. Despite the tremendous success of foundation models, effective adaptation to new tasks, particularly those with limited labels, remains an open question and lacks theoretical understanding. An emerging solution with recent success in vision and NLP involves finetuning a foundation model on a selection of relevant tasks, before its adaptation to a target task with limited labeled samples. In this paper, we study the theoretical justification of this multitask finetuning approach. Our theoretical analysis reveals that with a diverse set of related tasks, this multitask finetuning leads to reduced error in the target task, in comparison to directly adapting the same pretrained model. We quantify the relationship between finetuning tasks and target tasks by diversity and consistency metrics, and further propose a practical task selection algorithm. We substantiate our theoretical claims with extensive empirical evidence. Further, we present results affirming our task selection algorithm adeptly chooses related finetuning tasks, providing advantages to the model performance on target tasks. We believe our study shed new light on the effective adaptation of foundation models to new tasks that lack abundant labels. Our code is available at https://github.com/OliverXUZY/Foudation-Model_Multitask.

For agents

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

get_harvested_code_for_paper("2402.15017")
get_code_for_paper("2402.15017")
have("2402.15017")

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

curl https://syntology.ai/api/ran/2402.15017.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15017.svg)](https://syntology.ai/paper/2402.15017)

Connect an agent — have() is free.