Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
This paper proposes a differentiable architecture search method to automatically discover the optimal fusion scheme for combining image and prompt tokens in visual prompt tuning. The approach jointly optimizes learnable prompts and their fusion mechanisms, introducing affine transformation and cross-attention as new fusion schemes. Experiments on 34 datasets demonstrate consistent improvements over baselines, revealing that hybrid fusion better leverages layer semantics in Vision Transformers.
[2606.26379] Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
[Submitted on 24 Jun 2026]
Title:Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
View a PDF of the paper titled Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models, by Xi Xiao and 9 other authors
View PDF HTML (experimental)
Abstract:Visual prompt tuning has emerged as a parameter-efficient fine-tuning approach for adapting large-scale Vision Transformers (ViTs) to downstream tasks. As its learnable prompts are applied in input and feature spaces, prior to jointly going through attention in transformer layers, the most commonly used scheme for fusing image and prompt tokens is concatenation or addition. In this paper, we aim to study a fundamental yet essential problem in visual prompt tuning: whether a single fusion scheme tends to yield better results, and whether that would be beneficial to develop a hybrid fusion scheme. To this end, we formulate the task as a bi-level optimization problem, and solve it leveraging differentiable architecture search. In this context, the learnable prompts and their fusion schemes are jointly optimized. To enrich the search space in the architecture search, we propose two additional fusion schemes, namely, affine transformation and cross-attention, in addition to concatenation and addition. Extensive experiments on 34 datasets spanning VTAB-1k, FGVC, and HTA show consistent gains over prompt-tuning baselines. With a frozen ViT backbone, our method delivers a favorable accuracy--latency--parameter trade-off compared with VPT-Deep and recent variants. Our findings reveal that how prompts fuse with image tokens plays a significant role in visual prompt tuning, and a hybrid fusion fashion can more effectively leverage layer semantics of ViTs, contributing a novel perspective for visual prompt-tuning research.
Comments: ECCV 2026
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2606.26379 [cs.CV]
(or arXiv:2606.26379v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.26379
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Xi Xiao [view email] [v1] Wed, 24 Jun 2026 21:06:23 UTC (2,335 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models, by Xi Xiao and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)