搜索效率提高:相比现有技术,MoMa-LLM成功率高达97.7%,搜索路径更短,减少了不必要的动作。 实时动态应对:无论是在模拟环境还是现实家庭场景,MoMa-LLM都展现出了强大的适应能力和灵活性。 任务扩展性:它不仅能寻找物品,还可以解决模糊描述任务,比如“找到早餐用的东西”。MoMa-LLM的意义在于它不仅仅是一个“搜索工具...
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation. Project website: http://moma-llm.cs.uni-freiburg.de - robot-learning-freiburg/MoMa-LLM
Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text ...