vision-language-navigation 6 embodied-ai 3 vision-and-language 2 multimodal-learning 1 vision-language 1 vision-language-learning 1 vision-language-model 1 vision-language-models 1 vision-language-transformer 1 carla-simulator 1 end-to-end-autonomous-driving 1 openclip 1 3d-question-answering 1 large-language-models 1 multi-task-learning 1 referring-expressions 1 reinforcement-learning 1 multimodal-large-language-models 1 multimodal-deep-learning 1 multimodal-data 1 multimodal 1 internvl2 1 internvl 1 generative-ai 1 conversational-interface 1 conversational-bot 1 conversational-ai 1 conversational-agent 1 vision-language-pre-training 1 topological-maps 1