AI RESEARCH
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
arXiv CS.CV
•
ArXi:2605.11939v1 Announce Type: new Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods still struggle to maintain tail-class discriminability when adapting to class-imbalanced datasets. In this work, we propose cluster-aware neural collapse prompt tuning (CPT), which enhances the discriminability of tail classes in prompt-tuned VLMs without sacrificing their overall generalization.