SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.01759 · 2026

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

Qianru Sun, Yaoyao Liu, Zichen Tian

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2603.01759.json · badge: /api/ran/2603.01759.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
doem97/metalora canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
focal_loss Ran
ran; our contract draft was wrong, not the code
doem97/metalora/utils/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from tmlr-group/atol, is pointer only (licence: NONE) · get_code("4dcf06ba28983266")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from tmlr-group/atol, and GitHub detected no licence in that repository 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.

get_1d_sincos_pos_embed_from_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
doem97/metalora/models/satmae_vit.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from naver/croco, is pointer only (licence: NOASSERTION) · get_code("4bdd36eab04c3f62")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from naver/croco, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
doem97/metalora/models/satmae_vit.py
code served (permissive licence) · get_code("9417ae492629cf06")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (16, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function get_2d_sincos_pos_embed takes:
# - embed_dim: int, must be even (embedding dimension)
# - grid_size: int, size of the grid (height and width)
# - cls_token: bool, whether to prepend a cls token

ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (16, 8) — shape (16, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_model Not yet run
unverified (harvested, no recorded run)
doem97/metalora/clip/model.py
code served (permissive licence) · get_code("bd228a615e42622e")
How it ran

no invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
doem97/metalora/models/satmae_vit.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from naver/croco, is pointer only (licence: NOASSERTION) · get_code("4fd80de79832745d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from naver/croco, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

load Not yet run
unverified (harvested, no recorded run)
doem97/metalora/clip/clip.py
code served (permissive licence) · get_code("8f8de709efbc6a3d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 6 later) and 0 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
get_2d_sincos_pos_embed_from_grid 190 other papers
179 dated earlier, 2 the same month, 9 later · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_2d_sincos_pos_embed 95 other papers
92 dated earlier, 3 later · 33 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 92 more not named here
load 88 other papers
85 dated earlier, 2 later, 1 undated
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2206.01986 (2022-06)
Delving into the Openness of CLIP
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
and 85 more not named here
build_model 53 other papers
52 dated earlier, 1 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2211.09552 (2022-11)
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
and 50 more not named here
get_1d_sincos_pos_embed_from_grid 26 other papers
24 dated earlier, 1 the same month, 1 later · 11 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2207.06405 (2022-07)
Masked Autoencoders that Listen
2210.10716 (2022-10)
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
and 23 more not named here
focal_loss 14 other papers
12 dated earlier, 2 later
1906.07413 (2019-06)
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
2107.09249 (2021-07)
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
and 11 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

Training large foundation models from scratch for domainspecific applications is almost impossible due to data limits and long-tailed distributions -taking remote sensing (RS) as an example. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient finetuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module influence during fine-tuning. MetaPEFT dynamically adjusts three key factors of PEFT on RS images: module insertion, layer selection, and module-wise learning rates, which collectively control the influence of PEFT modules across the network. We conduct extensive experiments on three transfer-learning scenarios and five datasets in both RS and natural image domains. The results show that MetaPEFT achieves state-of-the-art performance in crossspectral adaptation, requiring only a small amount of trainable parameters and improving tail-class accuracy significantly. Our code is available at https://github.com/ doem97/metalora.

For agents

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

get_harvested_code_for_paper("2603.01759")
get_code_for_paper("2603.01759")
have("2603.01759")

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

curl https://syntology.ai/api/ran/2603.01759.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.01759.svg)](https://syntology.ai/paper/2603.01759)

Connect an agent — have() is free.