共计 286 篇文章

---

2025

11-26

Be My Eyes：通过多智能体协作将大型语言模型扩展到新模态

11-24

把MoE整合进LLaVA

11-20

ARC Is a Vision Problem

11-18

UpSafe℃： Upcycling for Controllable Safety in Large Language Models

11-17

Do Not Merge My Model！ Safeguarding Open-Source LLMs Against Unauthorized Model Merging

11-13

非文本的上下文学习

11-11

借助主动检索增强缓解大型视觉语言模型的幻觉问题

11-06

模型后面的层是否无用？

11-05

缓解多模态幻觉通过注意力引导的集成解码

11-05

大模型天生具有某些能力