1
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
多模态大模型新方法：可靠性优先的细粒度生成，平衡质量与可信度。
arXiv:2606.29573v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptio…