AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Controllable Federated Prompt Learning at Test Time

Rui Zhu, Liang Bai, Yanming Guo, Yirun Ruan, Tianyuan Yu, Zhihe Lu

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MoDA alignment score instead of Gini index only (ablation)COTE · CIFAR100 Avgaccuracy: 67.14 -> 71.08Improved
use MoDA alignment score instead of entropy only (ablation)COTE · CIFAR100 Avgaccuracy: 70.89 -> 71.08Improved
use MoDA alignment score instead of regularity index only (ablation)COTE · CIFAR100 Avgaccuracy: 67.15 -> 71.08Improved
add confidence-based sample partition (both branches) vs high-confidence branch only (ablation)COTE · CIFAR100 Avgaccuracy: 65.04 -> 71.08Improved
add confidence-based sample partition vs low-confidence branch only (ablation)COTE · ImageNet Avgaccuracy: 75.21 -> 81.44Improved
add confidence-based partition on ImageNet-R (ablation)COTE · ImageNet-Raccuracy: 89.37 -> 89.27No clear effect
increase stability coefficient lambda from 0.7 to 0.9 (ablation)COTE · CIFAR100 and ImageNet Avgaccuracy: best 71.08 and 81.44 at 0.9Improved
set phi to extreme values 0 or 1 instead of mid-range (ablation)MoDA · CIFAR100 and ImageNetaccuracyHurt
adaptive phi (auto) vs best fixed phi (ablation)MoDA · CIFAR100 and ImageNetaccuracyNo clear effect
personalize prompts via fine-tuning (PromptFL + FT) vs global PromptFLPromptFL · CIFAR100 OoCaccuracy: 62.30 -> 22.07Hurt
add generic TTA (TENT) on personalized promptPromptFL + FT · CIFAR100 Avgaccuracy: 65.04 -> 51.99Hurt
use COTE instead of TPT on out-of-client datapersonalized FPL · CIFAR100 OoCaccuracy: 19.24 -> 42.34Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy