Copertina

Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Yunbei, Cai, Chengyi, Liu, Feng, Hamm, Jihun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
di: Zhang, Yunbei, et al.
Pubblicazione: (2026)

OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation
di: Zhang, Yunbei, et al.
Pubblicazione: (2024)

DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
di: Zhang, Yunbei, et al.
Pubblicazione: (2024)

Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation
di: Wang, Janet, et al.
Pubblicazione: (2023)

Attribute-based Visual Reprogramming for Vision-Language Models
di: Cai, Chengyi, et al.
Pubblicazione: (2025)

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
di: Cai, Chengyi, et al.
Pubblicazione: (2025)

Bayesian-guided Label Mapping for Visual Reprogramming
di: Cai, Chengyi, et al.
Pubblicazione: (2024)

Sample-specific Masks for Visual Reprogramming-based Prompting
di: Cai, Chengyi, et al.
Pubblicazione: (2024)

Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
di: Zhang, Yunbei, et al.
Pubblicazione: (2026)

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
di: Wang, Janet, et al.
Pubblicazione: (2025)

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation
di: Chung, Yunsung, et al.
Pubblicazione: (2025)

Robust Adaptation of Foundation Models with Black-Box Visual Prompting
di: Oh, Changdae, et al.
Pubblicazione: (2024)

Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness
di: Hu, Xin, et al.
Pubblicazione: (2026)

Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
di: Zhang, Zhe, et al.
Pubblicazione: (2026)

Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning
di: Cai, Chengyi, et al.
Pubblicazione: (2026)

PPO-MI: Efficient Black-Box Model Inversion via Proximal Policy Optimization
di: Shou, Xinpeng
Pubblicazione: (2025)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
di: Hu, Kai, et al.
Pubblicazione: (2025)

Multimodal Representation Learning by Alternating Unimodal Adaptation
di: Zhang, Xiaohui, et al.
Pubblicazione: (2023)

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
di: Fan, Mingyuan, et al.
Pubblicazione: (2024)

Efficient Stitchable Task Adaptation
di: He, Haoyu, et al.
Pubblicazione: (2023)

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
di: Tariolle, Florent, et al.
Pubblicazione: (2026)

RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
di: Zhang, Serena, et al.
Pubblicazione: (2024)

ELASTIC: Efficient Once For All Iterative Search for Object Detection on Microcontrollers
di: Tran, Tony, et al.
Pubblicazione: (2025)

Language Models as Black-Box Optimizers for Vision-Language Models
di: Liu, Shihong, et al.
Pubblicazione: (2023)

Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
di: Sanga, Prabhav, et al.
Pubblicazione: (2025)

You Only Train Once
di: Sakaridis, Christos
Pubblicazione: (2025)

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
di: Huang, Zi-Xuan, et al.
Pubblicazione: (2024)

VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
di: Kumar, Somnath Sendhil, et al.
Pubblicazione: (2024)

Visual Variational Autoencoder Prompt Tuning
di: Xiao, Xi, et al.
Pubblicazione: (2025)

UCTB: An Urban Computing Tool Box for Building Spatiotemporal Prediction Services
di: Fang, Jiangyi, et al.
Pubblicazione: (2023)

Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation
di: Liang, Jian, et al.
Pubblicazione: (2024)

Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models
di: Chai, Weiheng, et al.
Pubblicazione: (2024)

Prompt-based Adaptation in Large-scale Vision Models: A Survey
di: Xiao, Xi, et al.
Pubblicazione: (2025)

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
di: Basani, Advik Raj, et al.
Pubblicazione: (2024)

Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
di: Swaminathan, Arjhun, et al.
Pubblicazione: (2025)

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
di: Shen, Zhirong, et al.
Pubblicazione: (2026)

Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport
di: Mehra, Akshay, et al.
Pubblicazione: (2024)

Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
di: Guichemerre, Alexis, et al.
Pubblicazione: (2024)

Data-free Defense of Black Box Models Against Adversarial Attacks
di: Nayak, Gaurav Kumar, et al.
Pubblicazione: (2022)

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
di: Wu, Xidong, et al.
Pubblicazione: (2024)