FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt Personalization

Paper recorded by Signals 4 on 2026-10-16 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-16 on arXiv · recorded by Signals 4 on 2026-10-19

Category: cs.CV · 计算机视觉 · first seen 2026-10-19

Abstract

Federated prompt learning enables vision-language models like CLIP to collaboratively adapt lightweight soft prompts across distributed clients without sharing raw data. However, existing federated prompt learning methods are designed primarily for supervised settings with labeled client data and assumed relatively stable training distributions. At test time, source-free federated prompt tuning re

Read on arXiv →