Aizah Arif

BiReg: Bilateral Regularized Kernel Adaptation for Training-Free Few-Shot Adaptation of Vision–Language Models

Large vision-language models (VLMs) demonstrate impressive zero-shot capabilities but exhibit limited adaptability in few-shot learning and domain transfer scenarios. Current adaptation methods present a critical tradeoff: gradient-based fine-tuning achieves strong performance but requires extensive computation and ris...

Bilateral Kernel Regularization for Few-Shot Adaptation of Large Vision-Language Models