Update mllm_papers.md

docs/mllm/mllm_papers.md

@@ -4,6 +4,7 @@
 
 ## 最新动态
 - 2024.11 [HourVideo: 1-Hour Video-Language Understanding](https://arxiv.org/abs/2411.04998) 李飞飞团队提出长视频理解评测集
+- 2024.11 [Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models](https://arxiv.org/abs/2411.04996)
 - 2024.11 [MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS](https://arxiv.org/pdf/2411.02571) 英伟达提出基于MLLM的通用多模态检索。
 - 2024.11 [Attacking Vision-Language Computer Agents via Pop-ups](https://arxiv.org/abs/2411.02391) 
 - 2024.11 [Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework](https://arxiv.org/abs/2411.01639) 提高多模态基础模型在处理不确定性时的能力，从而增强机器人在规划任务中的可靠性。