Jiaqi Wu

Jiaqi Wu

Postdoctoral Researcher at Tsinghua University

FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models

Published in International Conference on Computer Vision (ICCV 2025), 2024

This paper proposes Federated Discrete Prompt Tuning (FDPT) for black-box visual-language models, achieving efficient model fine-tuning while protecting data privacy.

Keywords: Federated Learning, Prompt Learning, Visual-Language Models, Multimodal Learning

Conference Ranking: CCF A

Authors: Jiaqi Wu, Simin Chen, et al.

Recommended citation: Jiaqi Wu, Simin Chen, et al. (2025). "FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models." ICCV 2025. (CCF A)