Pith. sign in

REVIEW 5 cited by

Neural Prompt Search

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.04673 v2 pith:LVFAD6BW submitted 2022-06-09 cs.CV cs.AIcs.LG

Yuanhan Zhang , Kaiyang Zhou , Ziwei Liu This is my paper
classification cs.CVcs.AIcs.LG
keywords promptvisionmodelsmodulesneuralnoahsearchtuning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Opto-ViT-v2: Noise-Resilient On-Chip Fine-Tuning for Photonic Near-Sensor Vision Transformer Accelerators

    cs.AR 2026-07 conditional novelty 6.0 of 10

    Opto-ViT-v2 performs on-chip fine-tuning of a vision transformer on a photonic accelerator by updating only ~8K electronic low-rank factors, recovering within 0.3–0.8% of clean-software accuracy under modeled photonic noise.

  2. DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A parameter-efficient video-text retrieval method that trains only 0.56M parameters on top of frozen CLIP and achieves 50.5% R@1 on MSRVTT.

  3. DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DA-VPT guides visual prompts with a proxy-anchor metric loss and dynamic class-to-prompt clustering, reporting consistent gains over VPT baselines across classification and segmentation.

  4. Regularizing Subspace Redundancy of Low-Rank Adaptation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    ReSoRA adds a penalty that reduces redundancy among rank-1 subspaces of LoRA-style adapters, producing modest accuracy improvements on vision-language retrieval and visual classification.

  5. Weight Spectra Induced Efficient Model Adaptation

    cs.LG 2025-05 reject novelty 4.0 of 10

    Fine-tuning mostly amplifies and reorients the top singular directions of weight matrices, and SpecLoRA learns to rescale a top-left block plus LoRA to improve PEFT performance.

Pith tools