1
Propose and Attend: Training-free MLLM Grounding Confidence via Multi-Token Localized Attention
多模态大模型定位幻觉问题新解法，无需训练即可评估置信度，基于多令牌局部注意力机制。
arXiv:2607.05978v1 Announce Type: cross Abstract: Multimodal large language models can emit localized predictions, bounding boxes for objects and temp…