1
Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning
提出「先分割再回答」新范式，让多模态大模型在视觉推理中实现像素级精准定位
arXiv:2607.05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception …