BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models

arXiv:2610.12907 · cs.CV, cs.LG · Submitted 2026-10-09 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: Accepted in Conference on Neural Information Processing Systems (NeurIPS), 2026

Code: https://github.com/payamsiabd/BLEND

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 1× in this paper · explained in 13 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
• Bayesian Principles Improve Prompt Learning In Vision-Language Models
• Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts
• Efficient Test-Time Prompt Tuning for Vision-Language Models
• LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions
• SemPT: Semantic Prompt Tuning for Vision-Language Models
• Fine-Grained Visual Classification of Aircraft
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models