Papers › Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

22 Feb 2024arXiv:2402.15017archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 8 ran (4 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

oliverxuzy/foudation-model_multitask officialmentioned in paperpytorchSyntology: 16 samples, 8 ran (4 instrument-failed) · 8 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
2ran
8unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from oliverxuzy/foudation-model_multitask. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

oliverxuzy/foudation-model_multitask official repository 16 samples, 8 ran (4 instrument-failed) · 8 unverified
AverageMeter in 26 papers finetune.py ran no licence file found · pointer only · 448391a260518c64 · report fixture: returned AverageMeter · level recorded 2026-09-22
Timer in 12 papers finetune.py ran no licence file found · pointer only · 103e5bf76abe5b7d · report fixture: returned Timer · level recorded 2026-09-22
count_params in 80 papers finetune.py ran · our draft was wrong no licence file found · pointer only · 57935c9233ae310a · report fixture: signature model:callable/0/?, return_str:bool/0/bool · returned str · level recorded 2026-09-22
decay_lr finetune.py ran · honoured contract no licence file found · pointer only · 05f178cf8f67fb2e · report fixture: signature epoch:int/0/int, n_epochs:int/0/int, lr:float/0/float, schedule:NoneType/0/? · returned float · level recorded 2026-09-22
make in 38 papers finetune.py ran · our draft was wrong no licence file found · pointer only · 5c0a845766c67c36 · report fixture: signature name:str/0/str, params:generator/0/?, lr:float/0/float, momentum:float/0/float, weight_decay:float/0/float, beta1:float/0/float, beta2:float/0/float · returned Adam · level recorded 2026-09-22
register in 66 papers datasets/datasets.py ran · our draft was wrong no licence file found · pointer only · 9687bf7a922f098a · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
time_str in 5 papers finetune.py ran · our draft was wrong fingerprinted no licence file found · pointer only · df8ef801f1f069b0 · report fixture: signature t:float/0/float · returned str · level recorded 2026-09-22
warmup finetune.py ran · honoured contract fingerprinted no licence file found · pointer only · b5536ea9ed2c47b3 · report fixture: signature low:float/0/float, high:float/0/float, epoch:int/0/int, n_epochs:int/0/int, batch:int/0/int, n_batches:int/0/int · returned float · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
finetune.py unverified no licence file found · pointer only · 3a86045f15981b84 · report
ensure_path finetune.py unverified no licence file found · pointer only · 34e85ca54daccd74 · report
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input
finetune.py unverified no licence file found · pointer only · 7d408a58c39fd05b · report
main in 235 papers finetune.py unverified no licence file found · pointer only · 19ca843d619cc77a · report
make in 38 papers datasets/datasets.py unverified no licence file found · pointer only · db58e5a4a5aafdab · report
make_path in 9 papers finetune.py unverified no licence file found · pointer only · 94b1635e5243cca8 · report
set_bn_eval finetune.py unverified no licence file found · pointer only · 08a4ae2c29e737a1 · report
set_log_path finetune.py unverified no licence file found · pointer only · f4bfac480be197ea · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for multitask finetuning approach (graph method: multitask finetuning approach). 14 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · 19ca843d619cc77a
  2. AverageMeter helper · level 1 · ran · 448391a260518c64
  3. Timer helper · level 1 · ran · 103e5bf76abe5b7d
  4. accuracy helper · level 0 · unverified · 3a86045f15981b84
  5. count_params helper · level 1 · ran · our draft was wrong · 57935c9233ae310a
  6. decay_lr helper · level 1 · ran · honoured contract · 05f178cf8f67fb2e
  7. ensure_path helper · level 0 · unverified · 34e85ca54daccd74
  8. log helper · level 0 · unverified · 7d408a58c39fd05b
  9. make helper · level 1 · ran · our draft was wrong · 5c0a845766c67c36
  10. make_path helper · level 0 · unverified · 94b1635e5243cca8
  11. set_bn_eval helper · level 0 · unverified · 08a4ae2c29e737a1
  12. set_log_path helper · level 0 · unverified · f4bfac480be197ea
  13. time_str helper · level 1 · ran · our draft was wrong · df8ef801f1f069b0
  14. warmup helper · level 1 · ran · honoured contract · b5536ea9ed2c47b3

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2402.15017") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections