4 papers
FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
Kun Zhai, Siheng Chen, Xingjun Ma +1
Federated Prompt Tuning (FPT) is an efficient method for cross-client collaborative fine-tuning of large Vision-Language Models (VLMs). However, models tuned using FPT are vulnerab…
TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers
Hengyuan Xu, Liyao Xiang, Borui Yang +3
Watermarking is a critical tool for model ownership verification. However, existing watermarking techniques are often designed for specific data modalities and downstream tasks, wi…
FedEGG: Federated Learning with Explicit Global Guidance
Kun Zhai, Yifeng Gao, Difan Zou +4
Federated Learning (FL) holds great potential for diverse applications owing to its privacy-preserving nature. However, its convergence is often challenged by non-IID data distribu…
Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
Junhao Ge, Zuhong Liu, Longteng Fan +5
End-to-end (E2E) autonomous driving (AD) models require diverse, high-quality data to perform well across various driving scenarios. However, collecting large-scale real-world data…