AI RESEARCH
Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
arXiv CS.CV
•
ArXi:2603.24181v1 Announce Type: new Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming against CLIP-based methods. Notably, this gap is surprising because many LVLMs use CLIP-pretrained vision encoders. Yet LVLMs are not inherently limited by CLIP's architecture with independent vision and text encoders.