1
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
DetPO提出结合多模态大模型的上下文学习，为少样本目标检测提供全新解法，已被欧洲会议接收。
arXiv:2603.23455v2 Announce Type: replace Abstract: Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detect…