Papers › Neural Prompt Search

Neural Prompt Search

9 Jun 2022arXiv:2206.04673archive 2025-07-28

Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu

The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-efficient tuning methods, such as learning adapter layers or visual prompt tokens, which allow a tiny portion of model parameters to be trained whereas the vast majority obtained from pre-training are frozen. However, designing a proper tuning method is non-trivial: one might need to try out a lengthy list of design choices, not to mention that each downstream dataset often requires custom designs. In this paper, we view the existing parameter-efficient tuning methods as "prompt modules" and propose Neural prOmpt seArcH (NOAH), a novel approach that learns, for large vision models, the optimal design of prompt modules through a neural architecture search algorithm, specifically for each downstream dataset. By conducting extensive experiments on over 20 vision datasets, we demonstrate that NOAH (i) is superior to individual prompt modules, (ii) has a good few-shot learning ability, and (iii) is domain-generalizable. The code and models are available at https://github.com/Davidzhangyuanhan/NOAH.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2206.04673")

Code

Syntology Ran 6 of 9 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ZhangYuanhan-AI/NOAH officialmentioned on GitHubtfMIT 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

9 samples harvested; 6 ran; 2 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · fixture could not drive it
1ran
3unverified

Licence: 0 of the 9 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 ZhangYuanhan-AI/NOAH. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

build_transform ZhangYuanhan-AI/NOAH/lib/datasets.py official repository ran MIT (permissive) · 4352f21759f08de9 · report
calc_dropout ZhangYuanhan-AI/NOAH/model/supernet_transformer_prompt.py official repository ran · honoured contract fingerprinted MIT (permissive) · 72a860a9aff50105 · report
drop_path ZhangYuanhan-AI/NOAH/model/utils.py official repository ran · fixture could not drive it MIT (permissive) · 39eace7e2822504f · report
gelu ZhangYuanhan-AI/NOAH/model/supernet_transformer_prompt.py official repository ran · honoured contract fingerprinted MIT (permissive) · 08a5be1ffa0676e3 · report
resize_pos_embed ZhangYuanhan-AI/NOAH/model/supernet_vision_transformer_timm.py official repository ran · fixture could not drive it MIT (permissive) · 191b2735955d18f4 · report
trunc_normal_ ZhangYuanhan-AI/NOAH/model/utils.py official repository ran · fixture could not drive it MIT (permissive) · 02566da69866c48c · report
build_dataset ZhangYuanhan-AI/NOAH/lib/datasets.py official repository unverified MIT (permissive) · 3d5d962b181c73fb · report
checkpoint_filter_fn ZhangYuanhan-AI/NOAH/model/supernet_vision_transformer_timm.py official repository unverified MIT (permissive) · 6d8a1f8a0697180f · report
sample_configs ZhangYuanhan-AI/NOAH/supernet_engine_prompt.py official repository unverified MIT (permissive) · 3f3ae80f9a34d92b · report

Tasks

Few-Shot LearningImage ClassificationNeural Architecture SearchPrompt EngineeringTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification OmniBenchmark NOAH-ViTB/16 Average Top-1 Accuracy 47.6 #1 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAdapterAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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