AI RESEARCH
Neutral-Reference Prompting for Vision-Language Models
arXiv CS.LG
•
ArXi:2605.15615v1 Announce Type: cross Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-off (BNT): improving performance on unseen (new) classes often degrades accuracy on known (base) classes. Addressing how to boost recognition of unseen classes without sacrificing known-class performance remains a central challenge. Existing work often simplistically attributes the BNT to overfitting on known classes.